The present invention makes it possible to more accurately detect interference caused by the simultaneous transmission of radio waves of the same frequency by a plurality of wireless stations. An interference detection system according to an embodiment of the present invention comprises: a main wave estimation unit 10 for estimating a temporary main wave AM-modulated wave AM_m(t) on the basis of a main wave frequency of a reception radio wave Rx(t) including at least a main wave and an AM component (t) of the reception radio wave Rx(t); an adaptive filter unit 20 for removing the temporary main wave AM-modulated wave AM_m(t) from the reception radio wave Rx(t); and an interference detection unit 30 for detecting the occurrence of interference on the basis of a canceller output e(t) of the adaptive filter unit 20.
Provided is a technology for managing movable devices. A device management system according to the present invention comprises a plurality of devices to be monitored and a monitoring server. The plurality of devices to be monitored are disposed under the monitoring server. Each device to be monitored transmits, to the monitoring server, the position information of the device to be monitored acquired from a GPS and the state information of the device to be monitored at arbitrary time intervals. The monitoring server automatically registers the position information of the device to be monitored received from the device to be monitored, and monitors the state of the device to be monitored.
H04Q 9/00 - Arrangements in telecontrol or telemetry systems for selectively calling a substation from a main station, in which substation desired apparatus is selected for applying a control signal thereto or for obtaining measured values therefrom
A radar system comprises a plurality of radar devices that detect an object by monitoring different areas. Each of the plurality of radar devices includes a display device. When the object is detected by any one of the plurality of radar devices, a display device of a first radar device that has detected the object produces a display indicating that the object has been detected, and a display device of a second radar device different from the first radar device produces a display indicating a position of the first radar device.
The purpose of the present invention is to provide technology by which a system as a whole can continue providing service, even when a device constituting the system fails. One embodiment of a monitoring system according to the present invention is a monitoring system in which a plurality of terminal devices and a monitoring server for monitoring the terminal devices are connected by a network, wherein the monitoring server comprises a failure handling database, and when a failure occurs in some of the terminal devices, the monitoring server changes the settings of the terminal devices other than the terminal devices in which the failure has occurred, in accordance with terminal device setting values stored in the failure handling database.
The purpose of the present invention is to provide technology for correcting a defective pixel even if a video output inversion function is used. For this purpose, one image capture device according to the present invention comprises: an imaging unit which captures an image and is capable of outputting a captured positive image and an inverted image obtained by inverting the positive image; a defective pixel detection unit which detects first defective pixel coordinates contained in the positive image and second defective pixel coordinates contained in the inverted image; a defective pixel information management unit which calculates third defective pixel coordinates obtained by inverting the second defective pixel coordinates; a storage unit which stores the first defective pixel coordinates and the third defective pixel coordinates; and a defective pixel correction execution unit which corrects a defective pixel in the inverted image on the basis of the first defective pixel coordinates and the third defective pixel coordinates stored in the storage unit.
A position detection system according to one embodiment of the present invention includes a camera 10 for shooting an object area, a measuring instrument 20 for acquiring a positional relation between the camera 10 and an object, and a position detection device 30 for detecting a position of the object on the basis of an image shot by the camera 10. The position detection device 30, in a preparation stage, performs processing that, on the basis of the positional relation between the camera 10 and the object at a plurality of points acquired using the measuring instrument 20, calculates a perspective projection conversion matrix M for converting coordinates of the object in the image shot by the camera 10 to an actual position of the object, and in an operation stage, performs processing that calculates the coordinates of the object in the image shot by the camera 10 and converts the coordinates to the actual position of the object using the perspective projection conversion matrix M.
Provided is a video system comprising a camera for capturing a video and a display device for displaying the video captured by the camera. The camera has an image sensor for capturing a video, an acceleration sensor for measuring acceleration on at least a Z-axis directed in the vertical direction, and an interface for outputting the photographed video and the acceleration on the Z-axis direction measured by the acceleration sensor. The display device has a display screen for outputting a video captured by the camera, and determines whether or not the video output from the camera is to be vertically inverted and displayed on the display screen according to whether the acceleration on the Z-axis direction output by the camera is positive or negative.
The present invention pertains to object detection based on point cloud data acquired by scanning a monitoring range, and provides a mechanism whereby both a stationary object and a moving object can be suitably detected. An object detection system according to one embodiment of the present invention comprises: a LiDAR 10 that acquires point cloud data by scanning a monitoring range; and an object detection server 20 that executes an object detection process on the basis of the point cloud data acquired by the LiDAR 10. In accordance with the setting of a number of accumulated frames for each area obtained by dividing the monitoring range, the object detection server 20 accumulates point cloud data of each area in the monitoring range for each among the number of accumulated frames set for said area and executes the object detection process on the basis of the accumulated point cloud data.
This packet transfer device transfers a packet via a plurality of communication paths independently provided between packet transfer devices facing each other, and comprises: an addition unit that makes an addition to the packet; a duplication unit that controls the number of packets to which the identifier is added; a packet transmission unit that transmits the duplicated packet to each of the plurality of communication paths; a calculation unit that calculates a communication environment of each of the communication paths with reference to the reception history of the packet; a storage unit that records statistical information including the calculated communication environment and/or communication path information indicating the transmission characteristic of the communication path; and an estimation unit that estimates a communication environment after a given time from the storage unit. The estimation unit retrieves, from the storage unit, statistical information approximate to current statistical information, and estimates a communication environment after the lapse of the given time from the present on the basis of statistical information constituted by the retrieved statistical information after the lapse of the given time.
The present disclosure provides an image processing technique for performing high-speed tracking of a detection target in wide area monitoring. An image processing device includes a video acquisition unit to acquire a first image, an object detection processing unit to execute an object detection process on the first image, specify a target object therein, and generate a first object detection result indicating a position of the target object in the first image, a tracking processing unit to acquire a target region image including the target object, generate a resized image by executing a resizing process, execute an object detection process on the resized image, and generate a second object detection result indicating a position of the target object therein, and an integration processing unit to generate a final object detection result by integrating the first and second object detection results.
Provided are wide dynamic range, multi-plate and single-plate color imaging devices capable of performing flexible dimming control for each color by means of minimally configured filters. The multi-plate imaging device comprises: a movable polarizing filter that polarizes incident light; a rotation mechanism that rotates the movable polarizing filter with respect to an optical axis; and fixed polarizing filters respectively mounted at a predetermined angle at the front surfaces of imaging elements for receiving red light and blue light. The imaging device dims the red light and the blue light by means of the angle of rotation of the movable polarizing filter. The single-plate imaging device comprises: a movable polarizing filter that polarizes incident light; a rotation mechanism that rotates the movable polarizing filter with respect to an optical axis; and an imaging element having a color Bayer array in which a polarizing filter is mounted at a predetermined angle on red and blue color filters. The imaging device dims the red light and the blue light by means of the angle of rotation of the movable polarizing filter.
In an image analysis system according to one embodiment of the present invention, when luggage and a person are detected from an image captured by an imaging device 10, an image analysis device 20 determines whether the luggage is in a state of possession by the person on the basis of the presence or absence of a connection between the luggage and the person. Further, after it has been determined that the luggage is in the state of possession by the person, if the state of possession has been removed and a given amount of time has passed in which the luggage is not in the state of possession, the image analysis device 20 determines that the luggage is a candidate for an item left unattended, and the person is a candidate for the person who left the same behind; moreover, if a connection regarding the luggage is subsequently detected with a different person from the candidate for the person who left the luggage behind, said different person is determined to be a candidate for a person who carried the luggage away.
[Abstract] [Problem] To provide an abnormality detection system and an abnormality detection method that can reduce discrepancy between a normal/abnormal determination by a simple comparison of pixel values and a normal/abnormaldetermination by human observation when an input image and an image that was outputted by AI are compared. [Solution] An abnormality detection system and an abnormality detection method for the same, said abnormality detection system comprising: a first AI model 213 that has been trained using normal images of a target object as training data; a reconstruction unit 203 that uses the first AI model 213 to generate reconstructed image data from captured image data; a second AI model 216 that has been trained so as to extract, from two items of image data having a difference, a difference that is close to perception by human observation; a difference extraction unit 205 that uses the second AI model 216 to extract difference image data from the captured image data and the reconstructed image data; and an abnormality extraction unit 206 that extracts an abnormal portion from the difference image data.
In the present invention, an image system comprises a camera for capturing images, and a display device for displaying the images captured by the camera. The camera has an imaging element for capturing images, and an image processing unit for processing the images captured by the imaging element. The image processing unit outputs a plurality of images having different capturing ranges.
09 - Scientific and electric apparatus and instruments
42 - Scientific, technological and industrial services, research and design
Goods & Services
High-frequency switching power supplies; camcorders; infrared cameras; wireless transmitters and receivers; computer programs, recorded, for processing digital images; computer hardware; computer memory devices; computer peripheral devices; data processing equipment; downloadable computer programs for network management for processing digital images Computer programming; development of computer platforms; computer systems design; image processing software design; monitoring of computer system operation by remote access; rental of computers; providing temporary use of on-line non-downloadable computer software programs for network management for processing digital images; software as a service (SaaS) services featuring software for processing digital images; providing virtual computer systems through cloud computing; platform as a service (PaaS) featuring computer software platforms for processing digital images; computer technology consultancy; technological consultancy services for digital transformation
An analysis server 101 of an image analysis system according to one embodiment of the present invention: acquires, by an image acquisition unit 201, an original input image received from a camera 102 and applies, when image conversion as preprocessing is set, the image conversion to the original input image as the preprocessing; applies, by an image conversion unit 203, image conversion different from the preprocessing to the original input image; provides, by an image inference unit 204, the input image before the image conversion by the image conversion unit 203 (the original or preprocessed input image) to an object detection AI model to thereby acquire a first inference result and provides the input image after the image conversion by the image conversion unit 203 to the object detection AI model to thereby acquire a second inference result; and integrates, by an inference result reflection unit 205, the second inference result with the first inference result, to thereby acquire a final inference result.
A radar device 200 according to one embodiment of the present invention is configured to: integrate (e.g., coherently integrate) the reception levels of reflected waves corresponding to radar transmission waves using one of two integration schemes, specifically coherent integration or incoherent integration; execute a process for detecting abnormalities on the basis of the result of integrating the reception levels of the reflected waves; and, in cases in which an abnormality candidate that could be an abnormality is detected through the detection process, integrate (e.g., incoherently integrate) the reception levels of reflected waves in the direction where the abnormality candidate was detected using the other of the two integration schemes in the next radar operation.
This data expansion device executes: a first conversion process for converting, by a domain inverter, a second learning sample into a pseudo first learning sample that simulates a first learning sample, and for converting, by a domain converter, the pseudo first learning sample into a pseudo second learning sample that simulates the second learning sample; a first calculation process for calculating a pseudo first loss value which is a loss value based on a second correct value, and a pseudo first output value which is an output value obtained as a result of inputting, to a reference model, the pseudo first learning sample outputted by the first conversion process; a second calculation process for calculating a second loss value based on the second learning sample, and the pseudo second learning sample; and a first learning process for training the domain inverter and the domain converter so that an integrated loss value obtained by integrating the pseudo first loss value calculated by the first calculation process and the second loss value calculated by the second calculation process becomes small.
An object of the present invention is to improve the accuracy of tracking based on image processing. The image processing system of the present invention includes an object detection unit that detects an object with respect to image data using a learning model, and an object tracking unit. The object tracking unit creates a reference template in which are set a cutout image obtained by resizing the detected object from image data of a predetermined number-th frame and center coordinates, creates a temporary template in which are set a cutout image obtained by resizing the detected object from image data of the next frame and center coordinates, extracts a template pair for which a match is established under a predetermined condition, and updates the reference template by creating a template in which are set a cutout image having pixel values obtained by taking into account a predetermined amount of a pixel value of the cutout image of the pair reference template and a pixel value of a cutout image of the pair temporary template and the center coordinates of the pair temporary template, and retains remaining reference templates and temporary templates for updating as reference templates.
The purpose of the present invention is to facilitate the setting of an appropriate distant area for realizing high-speed, high-accuracy object detection regardless of the camera installation conditions. An image processing device 120 according to the present disclosure comprises: a function for setting, on the basis of positions and sizes of a plurality of object frames (221, 222) that respectively surround a plurality of persons that are included in a camera image (200) that is captured in advance by an image capture device 110, a distant area that includes an area in which the sizes of the object frames in the image area of the camera image become equal to or less than a threshold value; and a function for generating, on the basis of a camera image that is captured during operation, a reduced image that is a reduction of the camera image and a trimmed image in which the distant area portion is trimmed from the camera image, inputting both the reduced image and the trimmed image into a low-resolution learning model to perform person detection, and synthesizing and outputting the detection result based on the reduced image and the detection result based on the trimmed image.
The train monitoring system in this example comprises cameras 110 (110A to 110D) installed on each car of a train, video display devices 130 (130A, 130) installed on both the leading and trailing cars of the train to display videos received from the cameras 110 on each car of the train, and video recording devices 140 (140A, 140B) installed on both the leading and trailing cars of the train to record the videos received from the cameras 110 on each car of the train. The cameras 110 on each car of the train distribute a live playback stream to the video display device 130 (130A, for example) on the leading car of the train, and distribute a video recording stream to the video recording device 140 (140B, for example) on the trailing car of the train.
This classification device executes: a calculation process for calculating a first training result evaluation value indicating the extent to which data being classified, to which no correct-answer label is attached, contributes to supplemental training of a prediction model that is capable of accessing a training dataset in which correct-answer labels are attached and that is trained using the training dataset, the calculation being carried out on the basis of a first degree of uncertainty indicating the level of ambiguity in a first prediction result outputted as a result of having inputted the data being classified to the prediction model; a classification process for classifying the data being classified as either one of supplemental training data or non-supplemental training data for the prediction model, the classification being carried out on the basis of the first training result evaluation value calculated through the calculation process; a setting process for configuring a setting so that a correct-answer label can be attached to the supplemental training data classified through the classification process; and a supplementation process for supplementing the training dataset with the supplemental training data to which the correct-answer label was attached in the setting process.
The present invention provides an outline correction processing device capable of obtaining a softening effect for sufficiently lightening wrinkles and spots, even when the wrinkles in and spots on the skin of a person captured by a television camera are clearly depicted. The outline correction processing device is provided with a first high-pass filter which has the function of emphasizing the outline section of an image signal and a second high-pass filter which has the function of weakening the outline section of the image signal. Said device corrects the outline section of a specific color component in the inputted image signal by switching between connecting the first high-pass filter and the second high-pass filter to the inputted image signal.
H04N 5/208 - Circuitry for controlling amplitude response for correcting amplitude versus frequency characteristic for compensating for attenuation of high frequency components, e.g. crispening, aperture distortion correction
H04N 5/14 - Picture signal circuitry for video frequency region
24.
IMAGE ANALYSIS SYSTEM AN UPDATE METHOD FOR MACHINE LEARNING MODEL
An image analysis system and update method for a machine-learning model are to update a model in operation 111 to a retrained model 121, wherein in an image analysis server 1 which analyzes shot images, a first inference unit 11 performs inference using the trained model in operation 111, a relearning unit 14 performs relearning to generate a retrained model, a second inference unit 12 performs inference using a retrained model 121, and a comparison unit 15 compares the execution results of the first inference unit 11 and the second inference unit 12 to determine whether or not to update the model in operation 111 to the retrained model 121.
A technique is provided for detecting the presence or absence of an abnormality with respect to an object appearing in a target image with high accuracy without using AI, even in an environment in which luminance values and colors are likely to fluctuate. An abnormality detection device (230) includes: an image input unit (232) for inputting an input image indicating an abnormality detection target object; a gradient distribution generation unit (234) for dividing the input image into predetermined regions and generating, for each region, a gradient distribution that indicates a distribution of a luminance gradient direction of the region; and an abnormality determination unit (236) for determining the presence or absence of an abnormality by analyzing the gradient distribution generated for each region.
09 - Scientific and electric apparatus and instruments
42 - Scientific, technological and industrial services, research and design
Goods & Services
Optical apparatus and instruments; measuring apparatus;
power distribution or control machines and apparatus;
high-frequency switching power supplies; electrical
communication machines and instruments; camcorders; infrared
cameras; remote control apparatus; intercommunication
apparatus; high-frequency apparatus; transmitters
[telecommunication]; wireless transmitters and receivers;
computer programs, recorded; computer hardware; computer
memory devices; computer peripheral devices; data processing
equipment; electronic publications, downloadable. Computer programming; development of computer platforms;
computer systems design; image processing software design;
monitoring of computer system operation by remote access;
rental of computers; providing computer programs on data
networks; software as a service [SaaS]; providing virtual
computer systems through cloud computing; platform as a
service [PaaS]; computer technology consultancy;
technological consultancy services for digital
transformation.
The purpose of the present patent is to provide an imaging device capable of obtaining an image with a deep depth of field even when an aperture is open. This imaging device comprises: an imaging element unit that separately receives visible light and near-infrared light, and outputs a visible light signal and a near-infrared light signal; and a video signal processing unit that extracts a contour component from a video by means of the near-infrared light signal, and superimposes the extracted contour component on a video of the visible light signal. The imaging device further comprises: a lens; an aperture that adjusts the amount of light entering the lens, and a control unit that controls the aperture opening, wherein the control unit opens the aperture in accordance with the luminance level of the video by means of the visible light signal.
G03B 11/00 - Filters or other obturators specially adapted for photographic purposes
G03B 15/00 - Special procedures for taking photographsApparatus therefor
H04N 23/45 - Cameras or camera modules comprising electronic image sensorsControl thereof for generating image signals from two or more image sensors being of different type or operating in different modes, e.g. with a CMOS sensor for moving images in combination with a charge-coupled device [CCD] for still images
H04N 23/55 - Optical parts specially adapted for electronic image sensorsMounting thereof
H04N 23/75 - Circuitry for compensating brightness variation in the scene by influencing optical camera components
The present invention provides a monitoring system that can reduce processing load on a monitor and that can reduce transmission data volume. A monitor 14 has a divided display mode for simultaneously displaying videos of a plurality of cameras by dividing a screen; and an enlarged display mode for displaying a video of one of the cameras on the whole screen. A camera 13 provided to each vehicle has: a memory 25 for storing information about a clipping range which is set for each of the cameras; a displaying video generation unit 22 for generating a full-size video or a partial video clipped from the full-size video on the basis of the information about the clipping range; and a displaying video transmission unit 26 for transmitting the full-size video or the partial video generated by the displaying video generation unit 22. In the divided display mode, the monitor 14 requests transmission of partial videos from the cameras 13 which are targets for displaying, whereas, in the enlarged display mode, the monitor 14 requests transmission of a full-size video from one of the cameras 13 which is a target for displaying.
A wireless communication control device for controlling a reflector that reflects radio waves transmitted from a base station, the wireless communication control device comprising: a calculation device that executes predetermined processing; and a storage device that is accessible by the calculation device. The storage device stores a correspondence relationship between each of a plurality of beams and a reflector that is installed in the radiation direction of radio waves of each of the beams. The calculation device records the communication quality of the communication with the terminal using each of the plurality of beams in the storage device. If there is a beam, the communication quality of which is below a predetermined threshold, the calculation device selects the reflector corresponding to the other beam. The calculation device controls the reflection angle of the selected reflector so that the communication quality in the area where the communication quality has deteriorated due to said beam is improved.
An Objective of the present invention is to improve the inter-camera cooperation in a monitoring system comprising multiple cameras each having a function to perform video analysis by use of an AI model. A monitoring system according to the present example comprises: multiple AI cameras 101 each having a function to perform video analysis by use of an AI mode; and an analyzing device 102 that generates the AI model used in the AI cameras 101. Each of the AI cameras 101 detects suspicious behaviors through video analysis using a particular-behavior detection AI model for detecting the suspicious behaviors. When suspicious behaviors are detected by any of the AI cameras 101, the analyzing device 102 generates a particular-person detection AI model for detecting a particular person (suspicious person) having done the suspicious behaviors, and transmits the particular-person detection AI model to each of the AI cameras 101. Each of the AI cameras 101 detects the suspicious person through video analysis using the particular-person detection AI model.
A skeleton detection system stores a target image for use in skeleton detection, and a plurality of skeleton detection models respectively corresponding to a plurality of skeleton definition models for defining different skeletons. The skeleton detection system determines a predetermined condition for the skeleton detection of the target image, selects a first skeleton detection model from the plurality of skeleton detection models based on a result of the determination, and executes the skeleton detection of the target image by the first skeleton detection model.
An imaging device using a CMOS imaging element includes a memory that stores, as a correction reference value, a gain exceeding a gain obtained by the imaging element and at which a linear fixed pattern noise starts to occur in a captured image; and an image processor that suppresses the fixed pattern noise when the gain exceeding the gain obtained by the imaging element exceeds the correction reference value. The captured image includes multiple pixel lines, each pixel in each of the pixel lines being arranged according to one of a plurality of color scheme patterns. The image processor suppresses the fixed pattern noise when a pixel line of the fixed pattern noise is not continuous in the same color scheme pattern, or when the pixel lines of the fixed pattern noise are continuous in the same color scheme pattern and the number of continuous lines is two.
H04N 25/677 - Noise processing, e.g. detecting, correcting, reducing or removing noise applied to fixed-pattern noise, e.g. non-uniformity of response for non-uniformity detection or correction for reducing the column or line fixed pattern noise
H04N 25/76 - Addressed sensors, e.g. MOS or CMOS sensors
The purpose of the present invention is to provide a surveillance system capable of more accurately detecting dangerous events at railroad crossings. The surveillance system comprises an imaging device and an analysis device. The analysis device includes a state analysis control unit and a state analysis unit. When detecting the approach of a train by analyzing an image acquired by the imaging device or on the basis of information notified from a state notification unit, the state analysis control unit instructs the state analysis unit to start analyzing the image within the railroad crossing. The state analysis unit uses the image acquired by the imaging device to detect and track a moving object within the railroad crossing. When it is determined by using at least a current moving speed of the moving object that a detection target cannot reach a set virtual line until the blocking of the railroad crossing is completed, the state analysis unit determines that a dangerous event occurs, and performs alarm processing.
G06V 20/54 - Surveillance or monitoring of activities, e.g. for recognising suspicious objects of traffic, e.g. cars on the road, trains or boats
G08B 25/00 - Alarm systems in which the location of the alarm condition is signalled to a central station, e.g. fire or police telegraphic systems
G08B 25/04 - Alarm systems in which the location of the alarm condition is signalled to a central station, e.g. fire or police telegraphic systems characterised by the transmission medium using a single signalling line, e.g. in a closed loop
[Problem] To provide a wireless communication system which realizes high-reliability or high-speed communication by effectively using a plurality of wireless devices. [Solution] This wireless communication system is configured such that: a line control device 2 on the transmission side generates packets in accordance with a high-reliability (HRE) communication method or a high-speed (HRA) communication method and causes a plurality of wireless devices 3 on the transmission side to transmit the packets; and a line control device 2 on the reception side receives the packets as input from a plurality of wireless devices 3 on the reception side, which have received the packets, outputs a packet, which has been received normally first, to a communication terminal 1 on the reception side in a case where the packet communication method is the HRE communication method, and rearranges the packets in a transmission order and outputs the packets to the communication terminal 1 on the reception side in a case where the packet communication method is the HRA communication method.
H04W 4/46 - Services specially adapted for particular environments, situations or purposes for vehicles, e.g. vehicle-to-pedestrians [V2P] for vehicle-to-vehicle communication [V2V]
H04W 84/18 - Self-organising networks, e.g. ad hoc networks or sensor networks
[Problem] To provide a mesh network system in which a decrease in throughput due to a hidden terminal problem can be suppressed. [Solution] A mesh network system according to an example of the present invention comprises: a flight-type mobile node 301 to be connected to a wireless network; and a plurality of fixed nodes 311-314 which constitute the wireless network and which are also connected to a wired network. The plurality of fixed nodes 311-314 each use an antenna pattern in which a horizontal gain is suppressed so that a carrier will not be sensed by fixed nodes adjacent to each other.
[Problem] To enable a remote ID transmitted by a target UAV to be received more reliably even when reception of the remote ID is difficult. [Solution] A UAV 31 for capturing is used for acquiring a remote ID of a target UAV 11. The UAV 31 for capturing is constructed by mounting a capture device 32 having a remote ID reception function on a UAV body 33 that performs a flight operation according to a control signal transmitted by a UAV transmitter 35 (controller).
09 - Scientific and electric apparatus and instruments
42 - Scientific, technological and industrial services, research and design
Goods & Services
(1) Optical apparatus and instruments; measuring apparatus; power distribution or control machines and apparatus; high-frequency switching power supplies; electrical communication machines and instruments; camcorders; infrared cameras; remote control apparatus; intercommunication apparatus; high-frequency apparatus; transmitters [telecommunication]; wireless transmitters and receivers; computer programs, recorded; computer hardware; computer memory devices; computer peripheral devices; data processing equipment; electronic publications, downloadable. (1) Computer programming; development of computer platforms; computer systems design; image processing software design; monitoring of computer system operation by remote access; rental of computers; providing computer programs on data networks; software as a service [SaaS]; providing virtual computer systems through cloud computing; platform as a service [PaaS]; computer technology consultancy; technological consultancy services for digital transformation.
38.
WIRELESS COMMUNICATION SYSTEM, TRANSMISSION METHOD AND RECEPTION METHOD
The present invention allows a gain control to be appropriately effected even when a frame including no preamble signal block is used for wireless communications. The following processes are effected in a transmission power control unit 106 of a transmission unit. Specifically, an automatic transmission gain control unit 201 multiplies a transmission signal by a gain value that is the difference between the power of a signal loop-backed from a power amplifier 109 and the power of the transmission signal. A fixed transmission gain multiplying unit 202 multiplies the transmission signal by a predetermined gain value or by the gain value used in the automatic transmission gain control unit 201 during the preceding frame. A selection unit 203 selects the transmission signal as gain-controlled by the automatic transmission gain control unit 201 in a case of a preamble signal block being included in the frame of the transmission signal and selects the transmission signal as gain-controlled by the fixed transmission gain multiplying unit 202 in a case of no preamble signal block being included in the frame of the transmission signal.
The purpose of the present invention is to provide an image processing means capable of performing fast tracking processing on a detection target in wide area monitoring. Thus, the present invention is configured as an image processing device including: a video acquisition unit (201) for acquiring a first image; an object detection processing unit (202) which executes predetermined object detection processing for the first image, specifies a target object in the first image, and generates a first object detection result indicating the position of the target object on an image; a tracking processing unit (203) which acquires a target area image including the target object on the basis of the first object detection result, generates a resized image by executing resizing processing, which is for converting the target area image to be of a predetermined size, executes predetermined object detection processing for the resized image, and generates a second object detection result indicating at least the position of the target object on an image; and an integration processing unit (204) which integrates the first object detection result with the second object detection result, thereby generating a final object detection result.
The purpose of the present invention is to provide an abnormality detection system that can detect an abnormal portion with higher accuracy using a DL model. The abnormality detection system comprises: a signal acquisition unit (201) for acquiring an input signal from a sensor; a mask generation unit (202) for generating a mask to be superimposed on the input signal; a mask superimposition unit (203) for generating a masked signal by superimposing, on the input signal, the mask generated by the mask generation unit (202); a signal reconstruction unit (204) for generating a reconstructed signal by reconstructing the masked signal generated by the mask superimposition unit (203); and an abnormality determination unit (205) for determining whether or not the input signal includes an abnormal portion on the basis of an error, in a mask region, between the input signal and the reconstructed signal. The signal reconstruction unit (204) reconstructs a region that is masked by using a deep learning model obtained by performing training using normal input signals.
[Problem] To facilitate a search for objects detected from within a wide area by a radar system comprising a plurality of radar devices. [Solution] A radar system of an embodiment of the present invention comprises a plurality of radar devices 20 that detect objects by monitoring mutually different areas. The plurality of radar devices 20 each have a display device 30. In a case where an object 15 is detected by any of the plurality of radar devices 20, a display device 30 of a radar device 20 that detected the object 15 (for example, a display device 30-2 of a radar device 20-2) produces a display indicating that the object 15 has been detected, and a display device 30 of a radar device 20 different from that radar device 20 (for example, a display device 30-1 of a radar device 20-1) produces a display indicating the position of the radar device 20 that detected the object 15.
A transmission-side communication apparatus comprises: a masking unit 302 that masks a part of data to be transmitted; a compression unit 304 that reversibly compresses or irreversibly compresses the masked data; and a transmission unit 305 that transmits the reversibly compressed or irreversibly compressed data to a reception-side communication apparatus. The reception-side communication apparatus includes: a reception unit 306 that receives data transmitted from the transmission-side communication apparatus; a decompression unit 307 that decompresses received data that has been reversibly compressed; and a restoration unit 308 that restores the mask area of decompressed data or the mask area of irreversibly compressed received data.
A coherent integration adjustment unit 123 of a radar device 100 calculates an appropriate number of coherent integrations for a reflected wave signal on the basis of weather data provided by a weather meter 500. If the calculated number differs from the current number of coherent integrations, the coherent integration adjustment unit 123 instructs a signal processing unit 108 to change the number of coherent integrations to the calculated number. The signal processing unit 108 changes the number of coherent integrations for the reflected wave signal in accordance with the instruction from the coherent integration adjustment unit 123.
The purpose of this invention is to improve the accuracy of tracking based on image processing. This image processing system is characterized by comprising an object detection unit that detects an object through a learning model with respect to image data, and an object tracking unit, the object tracking unit: creating a reference template in which are set center coordinates and a cutout image obtained by resizing the detected object from image data of a prescribed number-th frame; creating a temporary template in which are set center coordinates and a cutout image obtained by resizing the detected object from image data of the next frame; extracting a pair of templates matching under a prescribed condition; updating the reference template by creating a template in which are set the center coordinates of the paired temporary template and a cutout image having pixel values obtained by adding a prescribed weight of the pixel values of the cutout image of the paired temporary template and the pixel values of the cutout image of the paired reference template; and retaining the remaining reference templates and temporary templates to update as reference templates.
A seat monitoring system according to the present example is provided with: a pressure sensor 12 and a temperature sensor 13 provided at each seat in a passenger cabin; a CPU 18 (or a server 25) that determines the seat status of each seat in the passenger cabin, including whether each seat in the passenger cabin is in an occupied state or an unoccupied state, on the basis of the results of detection by the pressure sensor 12 and the temperature sensor 13; and a monitor 24 that displays a passenger-cabin monitoring screen 50 including a seat map indicating the seat status of each seat in the passenger cabin. This makes it possible to readily recognize the seat status in a passenger cabin in a train without requiring a crew member to visit the passenger cabin.
The present invention performs a search for an object safely and with ease. A scope control unit can simplify and recognize the positional relationship between a scope and a fallen object, as a result of a classification which is in accordance with the range of a distance R in fig. 4a. A prescribed angle range (target recognition range X) around a central axis Y is set as a visual range where the presence or absence of a fallen object (100) is recognized. If the situation at the top portion of fig. 4a is recognized, the scope control unit causes an audio output unit to execute periodic sound output such as shown at the bottom of fig. 4a.
G06F 3/01 - Input arrangements or combined input and output arrangements for interaction between user and computer
G06F 3/0481 - Interaction techniques based on graphical user interfaces [GUI] based on specific properties of the displayed interaction object or a metaphor-based environment, e.g. interaction with desktop elements like windows or icons, or assisted by a cursor's changing behaviour or appearance
In this example, a radar system is such that normally, each of a plurality of radar devices 100-1 to 100-6 monitors the monitoring area for the same using a radar signal that has been frequency modulated within a first modulation band, and when one of the plurality of radar devices 100-1 to 100-6 fails, at least one radar device (for example, radar device 100-1) adjacent to the radar device (for example, radar device 100-2) that has failed monitors the monitoring area of the radar device that has failed using a radar signal that has been frequency modulated within a second modulation band that is narrower than the first modulation band. As a result, even if one of the radar devices fails, it is possible to continue monitoring the monitoring area of the radar device.
[Problem] To provide a wireless communication system which enables efficient wireless power supply in an antenna extension wireless system. [Solution] This wireless communication system comprises a slave device 3 which performs wireless communication with a plurality of mobile devices 4 and which connects to a master device 2 serving as a consolidation device. In the wireless communication system, the slave device 3 connects to a wireless power supply device 6 that wirelessly supplies power to the mobile devices 4, detects the reception power of the mobile devices 4, and performs control to turn on/off a power supply operation of the wireless power supply device 6 in accordance with the magnitude of the reception power.
H02J 50/20 - Circuit arrangements or systems for wireless supply or distribution of electric power using microwaves or radio frequency waves
H02J 50/40 - Circuit arrangements or systems for wireless supply or distribution of electric power using two or more transmitting or receiving devices
H02J 50/80 - Circuit arrangements or systems for wireless supply or distribution of electric power involving the exchange of data, concerning supply or distribution of electric power, between transmitting devices and receiving devices
H04W 88/00 - Devices specially adapted for wireless communication networks, e.g. terminals, base stations or access point devices
Provided is a transmitter system which facilitates maintenance work, reduces costs during installation, and achieves space savings at an installation location. This transmitter system can seamlessly switch an output of an uninterruptible switch 5 from a currently-used transmitter to a spare transmitter, and can also seamlessly switch the output from the currently-used transmitter to a maintenance transmitter, by controlling a phase difference of an input signal to the uninterruptible switch 5 by means of a phase difference detecting unit 6, while ensuring satisfactory isolation by means of coaxial switches 3, 4, and can, in addition, be achieved using a small number of components, namely one uninterruptible switch 5 and two coaxial switches 3, 4, by means of a distributing and switching unit 15.
H04B 1/74 - Details of transmission systems, not covered by a single one of groups Details of transmission systems not characterised by the medium used for transmission for increasing reliability, e.g. using redundant or spare channels or apparatus
[Problem] To provide a communication device and a communication system that can realize frame aggregation appropriate in a state of a wireless network, prevent occupation of an unnecessary line, and detect and block malicious communication. [Solution] Provided are a communication device and a communication system in which a communication station quality management unit 114 of a network unit 11 acquires an identifier of a communication station from a reception frame, acquires communication quality information at a timing of reception of the reception frame from a signal quality acquisition unit 122, and further acquires the number of transmission and reception of frames in respective commutation stations from a transmission/reception counter 121, and an aggregation management unit 111a of a QoS function unit 111 determines an aggregation amount and an aggregation method for the corresponding communication station, on the basis of the quality information of the respective communication stations from the communication station quality management unit 114, the number of transmission and reception of the frames, and information on a communication method from a communication method function unit 113.
[Problem] To realize an enlarged wireless area and increased uplink output at a low cost. [Solution] A distributed antenna wireless system of the present embodiment includes: a plurality of antennas 201 that are individually distributed and arranged to support wireless communication (in particular, uplink) between a base station 103 and a terminal station 104; an aggregation device 205 that receives input, via a receiving unit 203, of wireless communication signals which from each of the plurality of antennas 201 and received by the antennas, and that synthesizes signals, from among those signals, that are determined to be uplink signals from the terminal station 104 to the base station 103; and a high-gain antenna 206 that is different from the antennas 201 and that sends the signals synthesized by the aggregation device 205 toward the base station 103.
H04B 7/024 - Co-operative use of antennas at several sites, e.g. in co-ordinated multipoint or co-operative multiple-input multiple-output [MIMO] systems
H04B 7/08 - Diversity systemsMulti-antenna systems, i.e. transmission or reception using multiple antennas using two or more spaced independent antennas at the receiving station
[Problem] To obtain a transmission device having a simple structure which has redundancy against failure of an FM modulator and does not require a switching operation. [Solution] A synchronous first modulator 11 and a synchronous second modulator 12 that are independent from one another and FM-modulate a carrier wave using a common audio signal are used, FM1 is generated by the synchronous first modulator 11, and FM2 is generated by the synchronous second modulator 12. Although the first synchronous modulator 11 and the second synchronous modulator 12 operate independently, the operations of said modulators are synchronized by a common reference signal being input. In the transmission device 1, the FM1 and FM2 are combined by a combiner 13 and output as an output signal. Therefore, no switching operation is performed in the transmission device 1, and thus the output signal is not interrupted at the time of switching.
[Problem] To provide radio equipment comprising a directional antenna, which: when installed in an enclosed space inside of a building, in a tunnel, underground, or the like, the directionality of the antenna is fixed or semi-fixed; and addresses the problem in which the orientations of beams of the directional antenna must be individually adjusted, and labor is required to perform these adjustments. [Solution] Provided are fixed radio equipment and a radio communication system in which, given that the angles of beams of the directional antenna are autonomously adjusted in radio communication, a sensor unit 34 detects the orientation and inclination at which the radio equipment is installed, and a correction unit 35 adjusts the orientation of the beams of the directional antenna on the basis of the installation orientation and inclination detected by the sensor unit 34.
The present patent is of a technique with which GOP-format video data outputted from a network camera is quickly displayed. In the train-monitoring system 100 of the present patent, a monitoring server 124 that controls a monitor 122 transmits a video request signal to a camera 121 when the display of the monitor 122 is turned on, and in response to receiving the video control signal during video data output, the camera 121 generates and outputs an I-frame ahead of schedule without waiting for the next I-frame generation timing.
This patent provides a communication system wherein passwords are managed per group and security is heightened. A group generation unit 300 generates groups for management, and generates an SSID 410 and a password 420 for each of the groups. A group configuration unit 310 sets the SSID 410 and the password 420 generated by the group generation unit 300 in a surveillance camera 1, and sets the password 420 in a terminal 2. A communication control unit 100 communicates with the terminal 2 set to a group via the SSID 410 and the password 420. A communication control unit 200 communicates with the surveillance camera 1 set to the group using the password 420.
To provide a detection device that prevents normality/abnormality determination from being made with an object to be detected being overlooked even when the object to be detected is shown in an extremely small area of an image, a detection device 100 comprises an image acquisition unit 202 that acquires a first image including an object to be detected, an image processing unit 301 that outputs a second image obtained by processing the first image, an AE processing unit 303 that outputs a third image obtained by processing at least the second image out of the first image and the second image by using a trained autoencoder, a calculation processing unit 304 that calculates a difference between the first image and the third image and outputs a fourth image, and a determination unit 305 that makes normality/abnormality determination on the basis of the fourth image.
[Problem] To provide an optical transmission system that can improve convenience by flexibly handling combinations of a great variety of communication providers, frequency bands, and bandwidths, and construct versatile wireless areas, without undergoing large-scale system changes. [Solution] In an optical transmission system according to the present invention, a plurality of wireless transmission/reception units 101 that store frequency information for performing mapping of digital signals corresponding to communication providers, frequency bands, and bandwidths, are detachably stored in a wireless transmission/reception unit storage unit 100 of a master station 10, a control unit 114 reads frequency information from frequency information storage units 116 of the wireless transmission/reception units 101 inserted to the wireless transmission/reception unit storage unit 100, generates mapping information, and outputs the mapping information to an FPGA 113, and the FPGA 113 performs mapping of digital signals from the plurality of wireless transmission/reception units 101 on the basis of this mapping information.
Provided are an information processing device and an information processing method that make it possible to automate determination of whether misses or mis-detections have occurred for photographed images and to efficiently acquire candidates for re-training data. According to the present invention, an information processing device and an information processing method involve an image analysis unit 103 that outputs a feature map that represents feature values that are based on confidence scores for a specific object from acquired image data, a feature map analysis unit 104 that analyzes the outputted feature map and evaluates the certainty of detection results, and a correct answer determination unit 105 that determines whether the object has been correctly detected in the image data from evaluation results for the feature map, creates correct detection data when the object has been correctly detected, and creates a candidate for re-training data when the object has not been correctly detected.
Provided are a learning data generation device, a learning data generation system, and a learning data generation method for automating the work of collecting and annotating missed image data. In this generation device, learning data generation system, and learning data generation method, an inference unit 121 of an object detection unit 12 infers object detection in a video frame by means of a learned model, an interpolation unit 122 detects, from a plurality of video frames over time for which the inference has been performed, missed video frames for which object detection with the learned model was not carried out, and was thus missed, and interpolates a detection result for the detected missed frames from the plurality of video frames over time, and a learning data generation unit 14 uses the interpolated detection result to generate learning data.
Provided is a focus control method for increasing the speed of focusing in medium- and long-distance monitoring. This focus control method is executed by an imaging system including: a camera provided with an imaging element and a lens having a variable focal length; and a control device for controlling modification of the focal length and focusing of the lens. First, a subject distance which is the distance between a subject and the camera is calculated. The lens is then focused in accordance with the calculated subject distance prior to completing modification of the focal length. The lens is focused in accordance with the distance prior to beginning modification of the focal length. In this way, the speed of focusing is increased.
G02B 7/28 - Systems for automatic generation of focusing signals
G02B 7/08 - Mountings, adjusting means, or light-tight connections, for optical elements for lenses with mechanism for focusing or varying magnification adapted to co-operate with a remote control mechanism
Provided are an image analysis device, an image analysis system, and an image analysis method capable of more accurate detection of a shielded object. The present invention comprises an image acquisition unit (301) which acquires a captured image; an image processing unit (303) which outputs an analysis result for an input image acquired by the image acquisition unit (301); and a correction data acquisition unit (302) which acquires data used for a correction condition, wherein the image processing unit (303) discriminates an event occurrence state in which a detection target object is determined to be present in the image on the basis of a detection condition of the detection target object, an event-free state in which the detection target object is determined not to be present in the image on the basis of a non-detection condition of the detection target object, and a neural state in which the detection target object is determined to be shielded by using a correction condition, and a condition of transition from the neutral state to the event occurrence state is set looser than a condition of transition from the event-free state to the event occurrence state.
In this transmission device of a duplex IF scheme, damage associated with signal switching is suppressed. A first system is switched to a second system at a time point A0, and then the second system is switched to the first system at a time point B0 upon recovery of the first system from failure. On a transmission side, a switching notification signal (P2) is not issued at a time point prior to A1 which is prior to A0 by T0, but a switching notification signal P2' is issued at the time point A1. After the issuance of the switching notification signal P2', the first system is switched to the second system at the time point A0. Then, at the time point A2 after the lapse of prescribed time T1 from A0, the issuance of the switching notification signal P2' is discontinued.
H04L 1/22 - Arrangements for detecting or preventing errors in the information received using redundant apparatus to increase reliability
H04B 1/74 - Details of transmission systems, not covered by a single one of groups Details of transmission systems not characterised by the medium used for transmission for increasing reliability, e.g. using redundant or spare channels or apparatus
An objective of the present invention is to provide a cleaning status detection system capable of automatically determining a cleaning status. The present invention comprises an image capturing device 1 and an image processing device 10. The image processing device 10 comprises an image determination unit 14 that identifies a cleaner on the basis of an image captured by the image capturing device 1 and determines a cleaning status in the image by specifying a cleaned range from the behavior of the cleaner. In addition, the cleaning status is determined to be uncleaned when there is a portion, of a detection region set in the image, that has not been cleaned.
The purpose of the present invention is to provide an imaging device and a video processing system that can obtain predetermined information related to an image while protecting image information at a higher level. This invention involves an imaging device (1) and a video processing device (5). The imaging device (1) captures a video to obtain an image, detects a predetermined area in the image, resizes the detected area to extract feature values of the resized detected area, and outputs an image obtained by placing a mask image (16-3), in which the extracted feature values are arranged two-dimensionally, on the detected area of the obtained image. The video processing device (5) receives the image output by the imaging device, obtains the feature values from the mask image (16-3), and performs an inference process on the basis of the feature values.
Provided are an image analysis system which suitably updates a learning model by comparing changes in the detection accuracy of a model in operation and a re-learning model, and an update method of a machine-learning model. The present invention is an image analysis system and an update method for a machine-learning model, wherein the image analysis system includes an image analysis server 1 which analyzes a captured image, and in which a first inference unit 11 performs inference by means of a trained model in operation 111, a retraining unit 14 performs retraining and generates a retrained model, a second inference unit 12 performs inference by means of the retrained model 121, a comparison unit 15 compares performance results of the first inference unit 11 and the second inference unit 12 and determines an update from the model in operation 111 to the trained model 121, and thus the update is suitably executed from the model in operation 111 to the retrained model 121 by comparing the execution results of the operation in model 111 and the retrained model 121.
Provided is a radar system which can more accurately capture the shape of an object detected by a radar device. The radar system comprises a radar device 100 that detects an object on a road surface that is an area to be monitored, a plurality of sensor devices 200 that are installed in respectively different positions and acquire shape information of the object, as viewed from an own position, detected by the radar device 100, and a display device 400 that displays an object shape image based on a plurality of pieces of the shape information acquired by the plurality of sensor devices 200.
In order to operate a power amplifier for synthesizing a plurality of amplifier circuits with high efficiency, the gate voltages of the field-effect transistors (FETs) of the plurality of amplifier circuits are adjusted according to an individual difference in saturated power between the amplifier circuits. Specifically, the output ratios of the amplifier circuits (AMP-4, 8) with low saturated power are reduced, whereas the output ratios of the amplifier circuits (AMP-2, 6) with high saturated power are increased. Thus, a device is operated with high efficiency.
Provided is a train monitoring system that can properly photograph passengers in vehicles away from cameras even if a platform has a curved shape. This train monitoring system comprises cameras (13) attached to the outer sides of vehicles (10) of a train so as to face in the travel direction of the train or in the direction opposite from the travel direction, a monitor (14) that displays images photographed by the cameras (13), and a control device (16) that performs a control such that photographic ranges in directions away from the side surface of the train in the images displayed on the monitor (14) at a prescribed station increase beyond a standard photographic range.
[Problem] To provide a radio device that can quickly and highly precisely determine whether there exists any radio interference and that further can send a notice of a risk in accordance with the degree of the radio interference, thereby improving safety. [Solution] This radio device determines whether there exists any radio interference occurring on a receiving side when a plurality of radio apparatuses use the same frequency to perform transmissions. A window processing unit 15 subjects a received signal having a carrier frequency as the center frequency to a window processing so as to perform following FFT processing in an optimum manner. A rate conversion unit 16 performs a rate conversion of the output signal from the window processing unit 15 by use of a high frequency, thereby outputting frames including a particular number of samples, while causing the frames to overlap each other. An FFT unit 17 performs the FFT processing of the output signal from the rate conversion unit 16 on a frame-by-frame basis, thereby outputting a relationship between the frequency and the level. A radio interference determination unit 18 detects the peaks of carriers outputted from the FFT unit 17, and determines a radio interference state when a plurality of peaks are detected.
[Problem] To provide a base station with which it is possible to reduce power consumption and to improve communication quality while achieving expansion of a coverage area. [Solution] A base station according to the present example comprises a plurality of RUs 402 arranged at intervals and performs antenna control on the basis of BF control information including a Beam ID. In the base station, as the antenna control, RU selection units 410 of a BBU 401 and a HUB 405 select an RU 402 preliminarily associated with the Beam ID included in the BF control information to use the RU 402 for wireless communication.
H04B 7/024 - Co-operative use of antennas at several sites, e.g. in co-ordinated multipoint or co-operative multiple-input multiple-output [MIMO] systems
H04B 7/06 - Diversity systemsMulti-antenna systems, i.e. transmission or reception using multiple antennas using two or more spaced independent antennas at the transmitting station
H04B 7/08 - Diversity systemsMulti-antenna systems, i.e. transmission or reception using multiple antennas using two or more spaced independent antennas at the receiving station
A radio communication system according to the present example comprises: a plurality of unattended movable bodies (M1, M2) that are capable of route diversity transport using a plurality of radio communication lines for data transport; and a regulation station 30 that collects the line states of the radio communication lines for the respective ones of the plurality of unattended movable bodies. On the basis of the line states of the radio communication lines collected for the respective ones of the plurality of movable bodies, the regulation station 30 transmits a control signal of the radio communication line to a particular unattended movable body so as to increase the number of unattended movable bodies for which the number of radio communication lines the line states of which satisfy a quality determination criterion is equal to or greater than a predetermined value (for example, two lines).
Provided is a monitoring system that allows an operator to quickly notice the occurrence of danger, while suppressing an increase in operational burden on the operator of a running train. The monitoring system is provided with a camera 21 mounted to each car of a train, a display device 23 for displaying camera footage, and an analysis device 26 for performing a danger sensing process for sensing danger that has occurred near a car. The display device 23 does not display the camera footage during entry and/or departure of the train with respect to a station platform. However, if danger is sensed by the danger sensing process, the display device 23 displays camera footage of the car in which the danger has been sensed, even during entry and/or departure.
A purpose of the present invention is to provide an imaging device with which, when gain is provided that exceeds the specifications of a CMOS imaging element, it is possible to suppress fixed pattern noise (FPN) generated by individual differences of the CMOS imaging element. This imaging device 1 comprises: a CMOS imaging element 11; a memory 13 in which gain obtained using the CMOS imaging element 11 is exceeded, and the gain at which linear FPN starts to occur in a captured image is stored as a correction reference value; and an image processing unit 12 that performs gain correction for suppressing FPN in the captured image when gain exceeding the gain obtained with the CMOS imaging element 11 exceeds the correction reference value.
The purpose of the present invention is to expand a detectable range without increasing the number of radar devices. A radar device according to one embodiment of the present invention comprises: first transceiving antennas (104-1, 105-1) that emit radar waves and receive reflected waves while rotating about a prescribed rotational axis; second transceiving antennas (104-2, 105-2) that emit radar waves and receive reflected waves while rotating about the same rotational axis as that for the first transceiving antennas. The first transceiving antennas and the second transceiving antennas are disposed so as to have mutually different antenna directions on an antenna rotation plane that is orthogonal to the rotational axis, and also have mutually different antenna tilts with respect to the antenna rotation plane.
In the present invention, the following are provided: a means for highly accurate detection, without the use of AI, of whether an abnormality is present/absent in an object captured in a target video even in an environment where a luminance value or color is likely to fluctuate. An abnormality detection device (230) includes: a video input unit (232) that inputs an input video showing a target object for abnormality detection; a gradient distribution generation unit (234) that divides the input video into prescribed regions and generates, for each region, a gradient distribution representing the distribution of the luminance gradient-direction of the relevant region; and an abnormality assessment unit (236) that analyzes the gradient distribution generated for each region, thereby assessing the presence/absence of an abnormality.
An objective of the present invention is to improve the performance of video analysis in a monitoring system comprising multiple cameras each having a function to perform video analysis by use of an AI model. A monitoring system according to the present example comprises: multiple AI cameras 101 each having a function to perform video analysis by use of an AI mode; and an analyzing device 102 that generates the AI model used in the AI cameras 101. The analyzing device 102: generates, on the basis of video and analysis result obtained by each of the multiple AI cameras 101, a general-purpose AI model usable in the multiple AI cameras; adjusts the general-purpose AI model for each of the AI cameras, thereby generating a dedicated AI model suitable for the video analysis in that AI camera; and transmits the general-purpose AI model or the dedicated AI model to each of the multiple AI cameras 101.
Provided is a high-frequency power supply device having a failure location estimating function for performing on-site repairs, which can even be handled by non-high-level engineers. This high-frequency power supply device, including a matching device (3) which imparts high-frequency electric power to a plasma processing device (1), is provided with: a monitoring means for monitoring various statuses within the plasma processing device while the matching device is operating; and a control circuit (21) which, if it is determined that any of the various statuses is abnormal, performs control to issue an alarm corresponding to the abnormality determination, to save, in a log, the status within the high-frequency power supply device, to estimate the failure location from the status content at the time the alarm was issued as the determination of the abnormality, and to display the estimation result using a display circuit (18).
The present invention provides a video processing device capable of efficiently carrying out an operation of applying labels to captured images. Thus, a video processing device 100 comprises: a moving image processing unit 19 which processes a video signal output by an image capturing element 2 into moving image files of prescribed periods and outputs said moving image files; a storage unit 17 which stores operator action data 170 that includes action content of the operator and processing content corresponding thereto; and a recognition processing unit 18 which determines the action content of the operator on the basis of sensor signals output by sensor elements 3, generates action recognition results information on the basis of the operator action data 170 in the storage unit 17, and outputs the result to the moving image processing unit 19. When the recognition processing unit 18 has output information relating to label application as the action recognition results information, the moving image processing unit 19 applies a label relating to said label application to the moving image file of the prescribed period which includes the point in time when the action recognition results information was output.
An objective of the present invention is to improve the inter-camera cooperation in a monitoring system comprising multiple cameras each having a function to perform video analysis by use of an AI model. A monitoring system according to the present example comprises: multiple AI cameras 101 each having a function to perform video analysis by use of an AI mode; and an analyzing device 102 that generates the AI model used in the AI cameras 101. Each of the AI cameras 101 detects suspicious behaviors through video analysis using a particular-behavior detection AI model for detecting the suspicious behaviors. When suspicious behaviors are detected by any of the AI cameras 101, the analyzing device 102 generates a particular-person detection AI model for detecting a particular person (suspicious person) having done the suspicious behaviors, and transmits the particular-person detection AI model to each of the AI cameras 101. Each of the AI cameras 101 detects the suspicious person through video analysis using the particular-person detection AI model.
Provided is a monitoring system with which it is possible to reduce the number of cases in which an intruding object is missed, while preventing a worker from being falsely sensed. The present invention comprises a camera 11 for capturing an image of a monitoring area, an image processing device 12 for performing a process for sensing an intruding object using an image captured by the camera 11, and a GPS terminal 14 carried by a worker performing prescribed work in the monitoring area. The image processing device 12 sets, as a mask region not subjected to the process for sensing an intruding object, a region in the image captured by the camera 11 that includes coordinates corresponding to a position measured by the GPS terminal.
G08B 13/196 - Actuation by interference with heat, light, or radiation of shorter wavelengthActuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems using image scanning and comparing systems using television cameras
G08B 25/00 - Alarm systems in which the location of the alarm condition is signalled to a central station, e.g. fire or police telegraphic systems
H04N 5/232 - Devices for controlling television cameras, e.g. remote control
H04N 7/18 - Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
The present invention provides a camera system for magnifying and monitoring a plurality of objects to be monitored, wherein the objects to be monitored are magnified without a decrease in resolution, and a loss from a screen region is minimized. A first camera device (50a) acquires wide-angle video data. A second camera device (50b) is controlled for panning, tilting, and zooming, and acquires magnified video data having a designated angle of view. A computer system (300): (a) extracts an object to be monitored from captured data from the first camera device or the second camera device; (b) calculates an expected showing time with respect to the object to be monitored; and (c) transmits a control signal to the second camera device to capture a magnified image with respect to an object to be monitored that has a shorter showing time among the objects to be monitored.
The present invention inexpensively provides a mechanism capable of detecting, with excellent accuracy, any matter attached to a lens surface of an imaging device. This imaging device 1 performs: a photographing control process for narrowing the aperture of a lens 11 to the utmost limit by a lens control unit 14 and exercising control, while the exposure time of an imaging element 12 is extended to the extreme by an exposure control unit 15, so that photographing is performed while changing the direction of photographing by a camera platform 19; and an attached matter detection process for detecting any matter attached to the lens surface on the basis of edge components included in a photographed image.
The present invention allows a gain control to be appropriately effected even when a frame including no preamble signal block is used for wireless communications. The following processes are effected in a transmission power control unit 106 of a transmission unit. Specifically, an automatic transmission gain control unit 201 multiplies a transmission signal by a gain value that is the difference between the power of a signal loop-backed from a power amplifier 109 and the power of the transmission signal. A fixed transmission gain multiplying unit 202 multiplies the transmission signal by a predetermined gain value or by the gain value used in the automatic transmission gain control unit 201 during the preceding frame. A selection unit 203 selects the transmission signal as gain-controlled by the automatic transmission gain control unit 201 in a case of a preamble signal block being included in the frame of the transmission signal and selects the transmission signal as gain-controlled by the fixed transmission gain multiplying unit 202 in a case of no preamble signal block being included in the frame of the transmission signal.
The purpose of the present invention is to provide an imaging device capable of obtaining a video output of only a necessary portion in a horizontal direction and increasing a frame rate. The imaging device includes: a photoelectric conversion element; a timing generation circuit that supplies a horizontal transfer pulse to the photoelectric conversion element; and a control circuit that controls the timing generation circuit so that the horizontal transfer pulse supplied from the timing generation circuit to the photoelectric conversion element has a first period or a second period that is faster than the first period. The output of the photoelectric conversion element includes a first region used as a video output and a second region not used as the video output. The control circuit controls the timing generation circuit so that the horizontal transfer pulse having the first period is supplied to the photoelectric conversion element to correspond to the first region, and the horizontal transfer pulse having the second period is supplied to the photoelectric conversion element to correspond to the second region.
H04N 5/345 - Extracting pixel data from an image sensor by controlling scanning circuits, e.g. by modifying the number of pixels having been sampled or to be sampled by partially reading an SSIS array
This skeleton detection system stores an object image from which a skeleton is detected and a plurality of skeleton detection models corresponding to a plurality of respective skeleton definition models which define different skeletons. The skeleton detection system: performs a decision under a predetermined condition on skeleton detection from the object image; selects a first skeleton detection model from the plurality of skeleton detection models on the basis of the decision result; and executes skeleton detection for the object image by means of the first skeleton detection model.
[Problem] To provide a wireless communication system having an option for implementing wired frame synchronization control in addition to frame synchronization control for wireless communication, and which utilizes wired synchronization control in a wireless communication section with much interference. [Solution] A wireless communication system in which a BS1 has an option for wired synchronization control in addition to wireless synchronization control. When the option is adopted in response to an instruction and the like from a BSM3, the BS1 initially performs wired synchronization control or, if the wired synchronization control cannot be performed, performs wireless synchronization control. In a BS (wired slave) 1b, a free-running counter unit 115 is reset by a synchronization code received in a wired manner, and the reset counter value is transmitted to a BS (wired master) 1a, and a delay time is detected by the BS (wired master) 1a.
Provided is a positioning system that is capable of highly accurately measuring a target position while preventing a computation amount from increasing. One example of this positioning system comprises a plurality of RDFs 10-1 to 10-6 that each estimate the direction of arrival (DOA) of a radio signal transmitted from an aircraft 40 that is a target for three-dimensional positioning and a positioning unit 20 for measuring the position of the aircraft 40 on the basis of the DOAs estimated by each of the RDFs and the positions of each of the RDFs. The positioning unit 20 has a factor graph structure formed using a plurality of nodes.
To provide a means of accurately recognizing, at low cost, the usage conditions of public transportation while also utilizing existing infrastructure, the present invention provides a passenger counting system (100) including imaging devices (105A, 105C, 105C, 213) installed so as to acquire images of the entrance and exit, the entrance, or the exit of a vehicle (212), and a passenger counting device (125) for counting the number of boarding/alighting passengers, the number of boarding passengers, or the number of alighting passengers of the vehicle, wherein the passenger counting device includes a reception unit (130) that receives the images from the imaging devices and a counting unit (140) that applies a predetermined image processing means to the images to thereby count the number of boarding and alighting passengers, the number of boarding passengers, or the number of alighting passengers of the vehicle, and outputs a count result. With this arrangement, an image acquired by an existing sensor already installed in a vehicle, such as a bus or a train, can be used to accurately count the number of boarding and alighting passengers, the number of boarding passengers, or the number of alighting passengers of the vehicle, thereby making it possible to recognize the performance of public transportation.
[Problem] To provide a mobile communication system which detects and blocks malicious wireless communication as abnormal wireless communication, so as to avoid unauthorized occupation of a wireless channel and secure the communication security and quality. [Solution] A mobile communication system in which: a frame transmitter-receiver unit 112 of a communication device 1 outputs control information of a received frame to a frame information output unit 114; the frame information output unit 114 outputs received frame information for extracting the feature amount of the frame to a control terminal 4; the control terminal 4 determines whether the received frame information is normal or abnormal on the basis of a white list or a black list; to the frame transmitter-receiver unit 112 of the communication device 1 and a relay device 3, access control information for prohibiting reception is output upon the abnormality determination and access control information for cancelling prohibition of reception is output upon the normality determination, so as to block or unblock the reception.
Provided are a communication device, a communication method, and a program, which are capable of ensuring communication quality, in multicast communication, by selecting an appropriate modulation scheme according to the line state of the communication station on the route specified by a multicast group, excluding the influence of other communication stations. The communication device performs multicast communication, at the time of reception, stores the reception quality by means of a network unit 10 as node quality information corresponding to the IP address of a node, at the time of transmission in the multicast communication, refers to the node quality information to obtain a minimum value having a lowest quality among the communication qualities corresponding to the IP addresses of the nodes on the route specified by the multicast communication group, and selects a modulation scheme on the basis of the minimum value.
H04W 40/30 - Connectivity information management, e.g. connectivity discovery or connectivity update for proactive routing
H04L 12/711 - Route fault prevention or recovery, e.g. rerouting, route redundancy, virtual router redundancy protocol [VRRP] or hot standby router protocol [HSRP] using path redundancy using M:N active or standby paths
H04W 4/06 - Selective distribution of broadcast services, e.g. multimedia broadcast multicast service [MBMS]Services to user groupsOne-way selective calling services
H04W 28/18 - Negotiating wireless communication parameters
H04W 84/18 - Self-organising networks, e.g. ad hoc networks or sensor networks
Provided is a positioning system capable of pairing a plurality of DOAs and a plurality of targets in an appropriate manner and measuring the respective positions of the targets. The multi-target positioning system according to the present example has: a pairing unit 22 that, on the basis of respective positions of a plurality of DOA sensors (11-1 to 11-6) and two DOAs estimated by the plurality of DOA sensors, performs a pairing process for performing classification into a DOA sensor group having a position relationship in which a first target is on the right side when viewed from a DOA sensor and a second target is on the left side when viewed from the DOA sensor and a DOA sensor group having a position relationship inverse to said position relationship; and a positioning unit 24 that performs a positioning process for measuring the respective positions of the first target and the second target on the basis of a result of the pairing process by the pairing unit 22 and the respective positions of the plurality of DOA sensors.
Provided are a camera 13 that is attached to the exterior of a railcar of a train and acquires an image of an area near a door of the railcar, a monitor 14 that displays a camera image acquired by the camera 13, and a grime detection unit 33 that executes a grime detection process for detecting grime on the front glass of the camera 13. The grime detection unit 33 is built into the camera 13, for example. The grime detection unit 33 determines an execution timing for the grime detection process on the basis of train information indicating an operational status of the train, and executes the grime detection process using a camera image obtained at the execution timing.
Provided are techniques for enabling collective confirmation of a video of an imaging region as a whole without performing compressive scaling of a high-resolution video during inspection of an object to be inspected for dust, scratch, or pixel defect, even when a low-resolution display device is used. This imaging device comprises: an imaging element for capturing a subject image from an optical system; a video dividing unit for dividing a high-resolution video of an imaging region as a whole into a plurality of regions to obtain a plurality of low-resolution videos; and a video composing unit for obtaining a single low-resolution video by superposing the plurality of low-resolution videos. The video composing unit obtains a single low-resolution video composed of pixels obtained by performing a predetermined process on the pixels of each low-resolution video having the same coordinates when the plurality of low-resolution videos are superposed. The predetermined process is a process for selecting pixels having a lowest luminance level.
Provided are an image analysis system, an image analysis method, and an image analysis program that make it possible to monitor the state of a specific object and quickly detect and report an abnormality without increasing the amount of processing. The image analysis system, the image analysis method, and the image analysis program are for monitoring the state of an object (a monitored object) present in a monitoring area. An image analysis server 1 divides an image of the area into a plurality of grids, creates a learned model obtained by learning, for each grid in which the monitored object is expected to be present, an image in which the monitored object is present and an image in which the monitored object is not present, and subsequently uses the learned model as a basis to determine whether the monitored object is present within the grids in an input image. It is thus possible to detect the state of a monitored object by simple processing of each grid.
The present invention stably achieves high reception performance through the combination of synchronous detection and diversity techniques. In a receiving device 1, a synthesis adjustment unit 10 is used for adjustment during diversity synthesis. To the synthesis adjustment unit 10, an I signal and a Q signal obtained from a br1 and a br2 are inputted, and on the basis of the I signal and the Q signal at the time of state determination, the current state can be determined as being any one of "00", "01", "10", and "11". On the basis of the result, a diversity synthesis unit 20 generates a diversity synthesis output using any of synthesis formulas. Thereafter, a demodulation processing unit 30 determines the mark/space from the I signal and the Q signal. Even when the symbols of the I signal and the Q signal are reversed through the synchronous detection units 161, 162, outputs from the br1 and the br2 during the diversity synthesis output are synthesized in a manner as to enhance each other. Accordingly, the determination can be performed properly.
H04L 27/227 - Demodulator circuitsReceiver circuits using coherent demodulation
H04B 7/08 - Diversity systemsMulti-antenna systems, i.e. transmission or reception using multiple antennas using two or more spaced independent antennas at the receiving station
96.
TIME INFORMATION ACQUISITION DEVICE AND SYNCHRONIZATION SIGNAL CONVERSION DEVICE
[Problem]: To provide a time information acquisition device and a synchronization signal conversion device that can generate a synchronization signal at low cost regardless of whether indoor or outdoor, and, in particular, can acquire time information by efficiently and surely selecting a channel having good wireless quality from a broadcast wave. [Solution]: In this time information acquisition device and this synchronization signal conversion device, a broadcast wave signal control unit 15, when selecting a time information acquisition channel from among terrestrial digital broadcasting channels, selects one of a designated channel search process, a priority channel search process, and an all channel search process in accordance with the number of a designated channel and the number of a priority channel inputted by a user. In the all channel search process, while all channels of a terrestrial digital broadcast wave are sequentially set to a broadcast wave signal reception unit 13, wireless quality of the set channels are acquired and stored. A channel having the best wireless quality among all the channels is set to the broadcast wave signal reception unit 13 as a time information acquisition channel and the broadcast wave signal reception unit 13 is caused to select said channel.
Radar devices 10-1 to 10-5 have, as operation modes, a narrow-band mode in which a distance resolution Δd1 is applied to perform a radar operation, and a wide-band mode in which a distance resolution Δd2 higher than the aforementioned distance resolution Δd1 is applied to perform a radar operation. A control device 20 causes all of the radar devices 10-1 to 10-5 to operate in the narrow-band mode until a foreign substance is sensed in a monitoring area of any of the radar devices. In addition, after a foreign substance has been sensed in a monitoring area of any of the radar devices 10-1 to 10-5, the control device 20 causes the affected radar device to operate in the wide-band mode so as to specify the position of the foreign substance, and stops operation of the other radar devices.
Provided are a terminal device and an RF power supply device that can intuitively and easily display the status information on the RF power supply in a process and can easily determine whether the state is good or bad and whether adjustment is necessary. Since a terminal device 14 connected to RF power supplies 10 displays, regarding status information, the powers of the traveling waves and the reflected waves of the plurality of RF power supplies 10 in bar graphs on a frequency base screen, and displays the phase of each RF power supply in a color-coded bar graph, the terminal device and the RF power supply device can recognize the status information that is intuitive and ease to understand, mainly for the frequency of each RF power supply as well as the phase thereof.
[Problem] To provide an information processing system, an information processing program, and a security camera system that aid in assessing the accuracy of the results of image detection by humans, and improve efficiency of detection result correction and learning data creation, in image analysis using machine-learning. [Solution] Provided is an information processing system, an information processing program, and a security camera system, wherein a main control device 12 obtains a region for a detection target and class information indicating the category of the detection target as detection results from an evaluation image. When regions of detection targets of the same class overlap to a specific degree of overlap threshold or more, the main control device 12 accepts, as detection results, the region having the highest confidence level indicating the probability or likelihood of a detection target being present, and thus correct regions can be selected on the basis of confidence, and detection results can easily be acquired, when regions overlap.
A mobile station 10a measures the current position of an antenna 11a of the station and detects the phase difference between a reception signal for radio waves 30 and a local frequency synchronized between mobile stations. Similarly, a mobile station 10b measures the current position of an antenna 11b of the station and detects the phase difference between a reception signal for radio waves 30 and the local frequency synchronized between the mobile stations. Subsequently, a radio wave direction detection device 13a installed in the mobile station 10a estimates the arrival direction of the radio waves 30 on the basis of the current positions of the antennas and the phase differences at the times of reception obtained by the mobile station 10a and mobile station 10b.
G01S 3/48 - Systems for determining direction or deviation from predetermined direction using antennas spaced apart and measuring phase or time difference between signals therefrom, i.e. path-difference systems the waves arriving at the antennas being continuous or intermittent and the phase difference of signals derived therefrom being measured
G01S 5/04 - Position of source determined by a plurality of spaced direction-finders
