A portable communication device includes a main housing, and a knob coupled to the main housing. The knob is rotatable about a first axis that extends into the main housing, and the knob includes a channel that extends partially circumferentially about the first axis. The portable communication device also includes a button coupled to the main housing. The button is moveable linearly along a second axis that is parallel to the first axis, and the button includes a projection that is sized and shaped to extend into the channel. The button is movable between a first position in which the projection is within the channel, and a second position in which the projection is outside of the channel.
System, device and method are provided for inspection of electronic products. The method includes receiving, at a server electronic processor, x-ray image(s) associated with an electronic device. Image analytics are performed on the x-ray image(s) to identify a plurality of different fragmented signature portions disposed within the electronic device. The plurality of fragmented signature portions are collected, and a determination is made whether the collected fragments are combinable to form a complete signature based on pre-approved fragment images and fragment location stored in a memory of the server. The server generates a notification indicating: a valid, non-counterfeit product in response to determining a complete combined signature, with no missing fragment; a counterfeit component or counterfeit module in response to a missing fragment; and a counterfeit electronic product in response to a determination of all fragments missing.
A voice intercom system and method therefor are disclosed. The method includes wirelessly transmitting intercom directory data to a smartphone. The intercom directory data facilitates generation, on the smartphone, of an intercom access directory interface having a plurality of call initiation selection options, each with respect to which a call to a respective call recipient can be attempted.
H04L 61/4535 - Network directoriesName-to-address mapping using an address exchange platform which sets up a session between two nodes, e.g. rendezvous servers, session initiation protocols [SIP] registrars or H.323 gatekeepers
H04M 11/02 - Telephonic communication systems specially adapted for combination with other electrical systems with bell or annunciator systems
H04N 7/18 - Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
H04W 4/33 - Services specially adapted for particular environments, situations or purposes for indoor environments, e.g. buildings
A method, system and computer program product for visual representation of an incident scene is disclosed. The method includes generating, using an at least one processor, a set of inputs for causing an at least one learning machine to create, for display on a screen, a visual representation of the incident scene corresponding to witness statements. The visual representation includes depictions of a plurality of scene elements. The method also includes providing the set of inputs to the at least one learning machine to cause the at least one learning machine to create the visual representation of the incident scene.
Examples provide a variable zoom imaging system including an image sensor (14), a set of illumination channels (18), and a current driver circuitry for driving the set of illumination channels (18). Each respective illumination channel includes a set of light sources and a lens, and is associated with a respective focus distance. An electronic processor (22) is configured to focus the image sensor (14) to an object of interest (46), determine a distance from the image sensor (14) to the object of interest (46), determine an exposure period for the image sensor (14), select a subset of illumination channels to activate based at least on the distance from the image sensor (14) to the object of interest (46), and capture a first image of the object of interest (46) using the image sensor (14) by sequentially activating and deactivating each selected illumination channel of the subset for first respective time frames within the exposure period.
H04N 23/56 - Cameras or camera modules comprising electronic image sensorsControl thereof provided with illuminating means
H04N 23/67 - Focus control based on electronic image sensor signals
H04N 23/741 - Circuitry for compensating brightness variation in the scene by increasing the dynamic range of the image compared to the dynamic range of the electronic image sensors
H04N 25/58 - Control of the dynamic range involving two or more exposures
7.
SYSTEMS AND METHODS FOR INSERTINGWATERMARKS IN RADAR SIGNALS FOR ELECTRONIC COUNTER-COUNTERMEASURES
Systems and methods for inserting watermarks in radar signals for electronic counter-countermeasures are provided. An example radar system generates a radar signal comprising a plurality of rising and falling edges and inserts a watermark into the radar signal by applying a time shift to a particular one of the rising and falling edges. The radar system then determines whether a received radar signal includes a time-shifted rising or falling edge corresponding to the inserted watermark and responsively determines whether the received radar signal is a skin return signal or an electronic countermeasure signal.
A system and computer-implemented method for responding to a potential or actual vehicle theft is disclosed. The system is installable within a parking facility that includes a fixed barrier structure around at least a portion of a perimeter of the parking facility to facilitate restriction of vehicle exit and entry to an at least one location where a respective at least one access-controlled gate or door is installed. The system also includes a camera that is configured to capture at least one image showing license plate characters of a license plate of a vehicle. A Field Of View (FOV) of the camera is arranged to include coverage of an area that is inside the parking facility and along a path leading to the at least one access-controlled gate or door.
Examples provide a variable zoom imaging system including an image sensor, a set of illumination channels, and a current driver circuitry for driving the set of illumination channels. Each respective illumination channel includes a set of light sources and a lens, and is associated with a respective focus distance. An electronic processor is configured to focus the image sensor to an object of interest, determine a distance from the image sensor to the object of interest, determine an exposure period for the image sensor, select a subset of illumination channels to activate based at least on the distance from the image sensor to the object of interest, and capture a first image of the object of interest using the image sensor by sequentially activating and deactivating each selected illumination channel of the subset for first respective time frames within the exposure period.
Techniques for reconfiguring a second camera based on a first camera are provided. An event of interest is identified at a first camera using a first analytic. The event of interest occurring in a portion of a field of view of the first camera. A second camera whose field of view includes at least a portion of the event of interest in a field of view of the second camera is identified. It is determined that the second camera is equipped with a second analytic, the second analytic not currently operating on the at least a portion of the event of interest in the field of view of the second camera. The second camera is reconfigured to perform the second analytic on the at least the portion of the event of interest in the field of view of the second camera.
A method, system and computer program product for visual representation of an incident scene is disclosed. The method includes generating, using an at least one processor, a set of inputs for causing an at least one learning machine to create, for display on a screen, a visual representation of the incident scene corresponding to witness statements. The visual representation includes depictions of a plurality of scene elements. The method also includes providing the set of inputs to the at least one learning machine to cause the at least one learning machine to create the visual representation of the incident scene.
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
G06F 3/04845 - Interaction techniques based on graphical user interfaces [GUI] for the control of specific functions or operations, e.g. selecting or manipulating an object, an image or a displayed text element, setting a parameter value or selecting a range for image manipulation, e.g. dragging, rotation, expansion or change of colour
09 - Scientific and electric apparatus and instruments
42 - Scientific, technological and industrial services, research and design
Goods & Services
Radio communications; Transmission and delivery of telecommunication services, namely, providing voice, text, data, pictures, music and video via wireless networks and two-way radio dispatching services Two-way radios; Gateway routers; Downloadable software for enabling mobile phones with push to talk capability Application service provider, namely, hosting, managing, developing, and maintaining applications, software, and web sites, in the fields of personal productivity, wireless communication, mobile information access, and remote data management for wireless delivery of content to handheld computers, laptops and mobile electronic devices; Software as a service (SAAS) services featuring software for connecting people and devices with push-to-talk communications
Techniques for executing additional analytics at an access control point are provided. A target at an access control point attempting to traverse the access control point is identified. The target is provided an indication that traversal of the access control point is delayed. Additional analytics resources are directed to the access control point. Additional analytics are run on the target using the additional analytics resources. The target is allowed to traverse the access control point once the additional analytics have completed.
Techniques for executing additional analytics at an access control point are provided. A target at an access control point attempting to traverse the access control point is identified. The target is provided an indication that traversal of the access control point is delayed. Additional analytics resources are directed to the access control point. Additional analytics are run on the target using the additional analytics resources. The target is allowed to traverse the access control point once the additional analytics have completed.
A communication system, method and device are provided for managing a post-incident response. The system includes a security system controller having a processor configured to receive a notification that a mass incident event, such as an active shooter event, has ended and send a prompt requesting in-room victim status information to a plurality of in-room communication device of the building. Analytics are performed by the processor on the received in-room victim status information to determine room priority. A post-incident workflow is triggered that generates a plurality of control signals indicative of each room priority and in-room victim status for each room. The plurality of control signals are sent to chirp generators of door access control devices associated with each room of the building. Each control signal controls chirp playout indicative of the room priority and victim status. A mutual aid responder, without access to a radio, can follow the audible chirps.
G08B 23/00 - Alarms responsive to unspecified undesired or abnormal conditions
G08B 3/10 - Audible signalling systemsAudible personal calling systems using electric transmissionAudible signalling systemsAudible personal calling systems using electromagnetic transmission
G08B 21/22 - Status alarms responsive to presence or absence of persons
17.
DEVICE, SYSTEM, AND METHOD FOR CONTROLLING VEHICLE-RELATED FUNCTIONALITY
A device, system, and method for controlling vehicle-related functionality is provided. A system comprises: a vehicle comprising: a vehicle display; a mobile device comprising: a mobile display, the vehicle and the mobile device communicatively coupled to each other; a transceiver; and a controller. The controller is configured to: determine, via the transceiver, whether the vehicle is a first vehicle or a subsequent vehicle to arrive at an incident scene. When the vehicle is the first vehicle to arrive at the incident scene, the controller selectively enables: a first application for presentation at the vehicle display; and a second application for presentation at the mobile display. When the vehicle is the subsequent vehicle to arrive at the incident scene, the controller selectively enables: a third application, different from the first application, for presentation at the vehicle display; and a fourth application for presentation at the mobile display.
G08G 1/0965 - Arrangements for giving variable traffic instructions having an indicator mounted inside the vehicle, e.g. giving voice messages responding to signals from another vehicle, e.g. emergency vehicle
B60K 35/00 - Instruments specially adapted for vehiclesArrangement of instruments in or on vehicles
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]
18.
DEVICE, SYSTEM, AND METHOD FOR CONTROLLING A VEHICLE-RELATED DISPLAY INTO AN EXITED OCCUPANT SUPPORT MODE
A device, system, and method for controlling a vehicle-related display into an exited occupant support mode is provided. A system comprises: a vehicle egress sensor; a first vehicle comprising: a vehicle display; a mobile device comprising: a mobile display, the first vehicle and the mobile device communicatively coupled to each other; and a controller. The controller is configured to: determine, via the vehicle egress sensor, that an occupant has exited the first vehicle, or a second vehicle proximal to the first vehicle; and in response, selectively enable an exited occupant support mode at one or more of the vehicle display and the mobile display.
A computer-implemented method of generating a trigger initiating an emergency incident response workflow and a device implementing the method is disclosed. Emergency notification data associated with at least one emergency notification reporting a first incident is received. Based on the emergency notification data, a first sensor data originating from one or more sensors is retrieved, the first sensor data associated with a time and location of the first incident. At least one alarm-escalating trigger is generated. The alarm escalating trigger comprises an alarm-escalating condition and a first-type emergency incident response workflow, the alarm-escalating condition being based on at least a portion of the first sensor data. The alarm-escalating trigger, when implemented by an implementing device, triggers the first-type emergency incident response workflow in response to receiving a second sensor data originating from one or more implementing sensors, the second sensor data meeting the alarm-escalating condition.
H04M 11/04 - Telephonic communication systems specially adapted for combination with other electrical systems with alarm systems, e.g. fire, police or burglar alarm systems
20.
METHOD OF GENERATING A TRIGGER INITIATING AN EMERGENCY INCIDENT RESPONSE WORKFLOW
A computer-implemented method of generating a trigger initiating an emergency incident response workflow and a device implementing the method is disclosed. Emergency notification data associated with at least one emergency notification reporting a first incident is received. Based on the emergency notification data, a first sensor data originating from one or more sensors is retrieved, the first sensor data associated with a time and location of the first incident. At least one alarm-escalating trigger is generated. The alarm escalating trigger comprises an alarm-escalating condition and a first-type emergency incident response workflow, the alarm-escalating condition being based on at least a portion of the first sensor data. The alarm-escalating trigger, when implemented by an implementing device, triggers the first-type emergency incident response workflow in response to receiving a second sensor data originating from one or more implementing sensors, the second sensor data meeting the alarm-escalating condition.
A device, system and method to control operation of a base station is provided. A computing devices communicates, to two or more spectrum controllers, respective authorization requests associated with a physical base station at a given location, the two or more spectrum controllers managed by different respective entities. The computing device receives, from the two or more spectrum controllers, one or more respective spectrum controller responses to the respective authorization requests. When the one or more respective spectrum controller responses include at least one authorization associated with the physical base station, the computing device provides, to the physical base station, permission to operate via respective RF transmissions.
A method and system for carrying out iterative appearance searching is disclosed. The method includes employing at least one first reference image to carry out a first instance, computer vision-driven appearance search of first video data captured across a respective first set of a plurality of first security cameras. The method also includes obtaining a second reference image, having a respective relevance confidence that satisfies a confidence threshold condition, from the portion of the first video data. The method also includes employing the second reference image for a second instance, computer vision-driven appearance search of second video data captured across a respective second set of a plurality of second security cameras.
G06V 10/764 - Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
G06V 10/82 - Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
G06V 20/40 - ScenesScene-specific elements in video content
G06V 20/52 - Surveillance or monitoring of activities, e.g. for recognising suspicious objects
23.
DIFFERENTIAL CONFIGURATION UPDATES FOR MOBILE DEVICES
A system includes memory hardware configured to store instructions and processing hardware configured to execute the instructions. The instructions include loading a legacy configuration file including a plurality of legacy blocks and loading an updated configuration file including a plurality of updated blocks. The instructions include, for each updated block, identifying one legacy block from the plurality of legacy blocks having a same type as the updated block and a payload representing a nearest match to a payload of the updated block and generating an update data object based on an identifier of the legacy block and an identifier of the updated block and adding the update data object to a difference file in response to the identified one legacy block and the updated block having matching payloads but different identifiers. The instructions include transmitting the difference file to a mobile device via a radio network to update the device.
A method and system for carrying out iterative appearance searching is disclosed. The method includes employing at least one first reference image to carry out a first instance, computer vision-driven appearance search of first video data captured across a respective first set of a plurality of first security cameras. The method also includes obtaining a second reference image, having a respective relevance confidence that satisfies a confidence threshold condition, from the portion of the first video data. The method also includes employing the second reference image for a second instance, computer vision-driven appearance search of second video data captured across a respective second set of a plurality of second security cameras.
G06V 20/52 - Surveillance or monitoring of activities, e.g. for recognising suspicious objects
G06V 40/20 - Movements or behaviour, e.g. gesture recognition
G06V 20/58 - Recognition of moving objects or obstacles, e.g. vehicles or pedestriansRecognition of traffic objects, e.g. traffic signs, traffic lights or roads
25.
SYSTEM AND METHOD FOR SELECTING A GENERATED IMAGE THAT IS REPRESENTATIVE OF AN INCIDENT
Techniques for selecting a generated image that is representative of an incident are provided. An initial summary of an incident is generated using an artificial intelligence processing tool. At least two images based on the initial summary are generated using an artificial intelligence image generation tool. For each of the at least two images, a subsequent summary is generated using an artificial intelligence image to text generation tool. The initial summary is compared to each of the subsequent summaries. The generated image associated with the subsequent summary that is most similar to the initial summary is selected as representative of the incident.
Techniques for selecting a generated image that is representative of an incident are provided. An initial summary of an incident is generated using an artificial intelligence processing tool. At least two images based on the initial summary are generated using an artificial intelligence image generation tool. For each of the at least two images, a subsequent summary is generated using an artificial intelligence image to text generation tool. The initial summary is compared to each of the subsequent summaries. The generated image associated with the subsequent summary that is most similar to the initial summary is selected as representative of the incident.
Techniques for adjusting audio attributes for off-focus audio of a device are provided. An indication that audio attributes for on-focus audio are being adjusted are received at the device. The indication is received via an audio control of the device. A priority level of an application having the on-focus audio is determined. An event based on the priority level is determined. The audio attributes for on-focus audio are adjusted. The audio attributes for off-focus audio are adjusted upon occurrence of the event.
A method and system for controlled absence of moving objects from the field of view of a camera during a defined time period is disclosed. When data generated by an at least one electronics device or a respective controller thereof confirms that the physical environment requirements of the at least one electronics device will be met, or confirms that the at least one electronics device will be controlled to meet the operational requirements, the video camera is allowed to enter a mode where the capturing of the video is impeded during the time period. Conversely, when the data indicates that the physical environment requirements will not be met, or that the at least one electronics device will not be controlled to meet the operational requirements, the system ensures that the capturing of the video is not impeded during the time period.
Systems and methods for virtual assistant based cargo inspection. The method includes automatically inspecting a subset of cargo using a first recorded video associated with the cargo and generating a second recorded video by annotating the first recorded video including annotations for a second subset of the cargo identified for manual inspection. The method also includes accessing, using a portable communications device, a virtual assistant feature of the portable communications device. In response to receiving one or more prompts via the virtual assistant feature, the method includes receiving the second recorded video and generating an interactive display for displaying the second recorded video. In response to receiving one or more prompts via the virtual assistant feature, the method also includes detecting an interaction with the annotations of the second recorded video and providing, using the virtual assistant feature, a recommendation corresponding to the interaction via a human machine interface.
A system includes an in-vehicle assistant (IVA) platform and a mobile communication device. The IVA platform includes a first electronic processor, a first display, and a first communications interface. The mobile communication device includes a second electronic processor, a second display, and a second communications interface. At least one of the first electronic processor or the second electronic processor is configured to access a user profile, parse the user profile to identify a set of applications authorized for use by the user profile, the set of applications including a first application and a second application, generate and render a first graphical user interface (GUI) on the first display, generate and render a second GUI on the second display, render the first application on the first GUI and not on the second GUI, and render the second application on the second GUI and not on the first GUI.
A device, system and method to control network load at a base station is provided. A computing device determines a network loading level on a given sector of a base station, the base station in communication with wireless cameras categorized according to rank. When the network loading level exceeds a first threshold, the computing device adjusts a respective scene classification threshold of a lowest rank group of the cameras to a value that decreases a likelihood of scenes of the lowest rank group of the cameras being classified at a higher scene interest level. The scenes classified according to the higher level are streamed by the cameras at a quality higher than other scenes classified to a lower scene interest level, thereby controlling the cameras of the lowest rank, that generate respective scenes according to the lower level, to lower their respective network loading on the given sector.
A device, system and method to control network load at a base station is provided. A computing device determines a network loading level on a given sector of a base station, the base station in communication with wireless cameras categorized according to rank. When the network loading level exceeds a first threshold, the computing device adjusts a respective scene classification threshold of a lowest rank group of the cameras to a value that decreases a likelihood of scenes of the lowest rank group of the cameras being classified at a higher scene interest level. The scenes classified according to the higher level are streamed by the cameras at a quality higher than other scenes classified to a lower scene interest level, thereby controlling the cameras of the lowest rank, that generate respective scenes according to the lower level, to lower their respective network loading on the given sector.
Examples provide an imaging system including an image sensor; and an electronic processor in communication with the image sensor. The electronic processor is configured to determine a set of imaging parameters, and, for each iteration included in an iteration set, update the set of imaging parameters by: receiving an image captured by the image sensor using the set of imaging parameters, performing object recognition on the image to detect an object of interest, determining an object recognition confidence score, determining a set of external factors based on the image and/or information from a second sensor, linking the set of imaging parameters and the set of external factors to the object recognition confidence score, and training a predictive model for updating the set of imaging parameters using the object recognition confidence score, the set of imaging parameters, and the set of external factors.
Techniques for reducing resources used for uploading a video to be indexed for searching at a cloud search service are provided. A file containing the video is received at an on premise client application. The application processes the file with an event detector to detect at least one event of interest based on a first set of event detection criteria. The at least one event of interest is sent to the cloud searching service. The cloud searching service classifies at least one object in the at least one event of interest. The cloud searching service identifies a second set of event identification criteria based on the classification. The cloud searching service sends feedback to the application for event detection and sending events based on the second set of event identifying criteria. The application modifies the first event detection criteria based on the feedback to create new event detection criteria.
G06F 16/783 - Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
An imaging system including an image sensor (14); and an electronic processor (18) in communication with the image sensor (14). The electronic processor (18) is configured to determine a set of imaging parameters (30), and, for each iteration included in an iteration set, update the set of imaging parameters (30) by: receiving an image captured by the image sensor (14) using the set of imaging parameters (30), performing object recognition to detect an object of interest, determining an object recognition confidence score, determining a set of external factors based on the image and/or information from a second sensor, linking the set of imaging parameters (30) and the set of external factors to the object recognition confidence score, and training a predictive model (34) for updating the set of imaging parameters (30) using the object recognition confidence score, the set of imaging parameters (30), and the set of external factors.
A device, system and method to log a communication device into services using a device identifier is provided. An identity management (IM) computing device receives, from a certificate authority, a first digital certificate, and further receives from a given communication device, a second digital certificate and a device identifier associated with the given communication device. The IM computing device successfully validates the second digital certificate using the first digital certificate, obtains a user identifier associated with the device identifier, and issues, to the given communication device, one or more tokens that include the user identifier, the one or more tokens enabling the given communication device to log into one or more services using the user identifier.
H04L 9/32 - Arrangements for secret or secure communicationsNetwork security protocols including means for verifying the identity or authority of a user of the system
The present invention relates to a mounting apparatus and a holster having a bracket with a D-stud with a radial pattern of detent pockets. The D-stud allows the bracket to rotate in a ratcheting manner in a first range of motion and freely rotate in a second range of motion. The free rotation of the second range of motion allows the D-stud to automatically recover from a vertical position to a non-vertical position.
A method and system for analytics selection based on pursuit-context details is disclosed. The method includes tracking a pursuer object and a pursued object, and using analytics on video or image data corresponding to the pursuer object and/or the pursued object to determine at least one pursuit-context detail. The pursuit-context detail(s) are matched to a select one of a plurality of object behavior-targeted analytics.
Examples provide an imaging system including an electronic processor configured to obtain video data of a scene including a region of interest including a plurality of frames, determine a total number of detected humans in the region of interest of a current frame of the plurality of frames, determine a number of running humans in the region of interest of the current frame, and determine a probability associated with the number of running humans in the region of interest of the current frame and the total number of detected humans in the region of interest of the current frame based on accumulated statistics for the region of interest. In response to determining that the probability is less than a threshold probability, the electronic processor generates an alert indicating a stampede is detected in the region of interest.
Techniques for reducing resources used for uploading a video to be indexed for searching at a cloud search service are provided. A file containing the video is received at an on premise client application. The application processes the file with an event detector to detect at least one event of interest based on a first set of event detection criteria. The at least one event of interest is sent to the cloud searching service. The cloud searching service classifies at least one object in the at least one event of interest. The cloud searching service identifies a second set of event identification criteria based on the classification. The cloud searching service sends feedback to the application for event detection and sending events based on the second set of event identifying criteria. The application modifies the first event detection criteria based on the feedback to create new event detection criteria.
Devices, systems, and methods for automatically captioning images using swipe gestures as inputs. One example apparatus includes an electronic processor. The electronic processor is configured to receive an image. The electronic processor is configured to control a display to display the image. The electronic processor is configured to detect a first object in the image. The electronic processor is configured to detect a second object in the image. The electronic processor is configured to receive, from the display, a first swipe gesture. The electronic processor is configured to, responsive to receiving the first swipe gesture, determine a direction of the first swipe gesture relative to the first object and the second object. The electronic processor is configured to determine a word choice based on the first direction. The electronic processor is configured to generate a caption describing the image based on the word choice.
G06V 20/70 - Labelling scene content, e.g. deriving syntactic or semantic representations
G06F 3/04883 - Interaction techniques based on graphical user interfaces [GUI] using specific features provided by the input device, e.g. functions controlled by the rotation of a mouse with dual sensing arrangements, or of the nature of the input device, e.g. tap gestures based on pressure sensed by a digitiser using a touch-screen or digitiser, e.g. input of commands through traced gestures for inputting data by handwriting, e.g. gesture or text
A device, system and method to initiate a communication between communication devices based on audio input is provided. A computing device converts audio input from a first communication device into phonetic data corresponding to a target name from the audio input, and selects, using a machine learning algorithm, from names that potentially match the target name, a particular name as a match, using as input to the algorithm: the phonetic data; and non-phonetic data associated with one or more of the audio input, and at least one of the names. The computing device: initiates a communication between the first communication device, and a second communication device associated with the particular name; receives, from one or more of the first and second communication devices, feedback indicating whether the match of the particular name and the target name is positive or negative; and trains the machine learning algorithms using the feedback.
G10L 17/14 - Use of phonemic categorisation or speech recognition prior to speaker recognition or verification
G06V 40/10 - Human or animal bodies, e.g. vehicle occupants or pedestriansBody parts, e.g. hands
G06V 40/70 - Multimodal biometrics, e.g. combining information from different biometric modalities
G10L 17/02 - Preprocessing operations, e.g. segment selectionPattern representation or modelling, e.g. based on linear discriminant analysis [LDA] or principal componentsFeature selection or extraction
G10L 17/04 - Training, enrolment or model building
G10L 17/10 - Multimodal systems, i.e. based on the integration of multiple recognition engines or fusion of expert systems
43.
DEVICE, SYSTEM, AND METHOD TO INITIATE A COMMUNICATION BETWEEN COMMUNICATION DEVICES BASED ON AUDIO INPUT
A device, system and method to initiate a communication between communication devices based on audio input is provided. A computing device converts audio input from a first communication device into phonetic data corresponding to a target name from the audio input, and selects, using a machine learning algorithm, from names that potentially match the target name, a particular name as a match, using as input to the algorithm: the phonetic data; and non-phonetic data associated with one or more of the audio input, and at least one of the names. The computing device: initiates a communication between the first communication device, and a second communication device associated with the particular name; receives, from one or more of the first and second communication devices, feedback indicating whether the match of the particular name and the target name is positive or negative; and trains the machine learning algorithms using the feedback.
Techniques for resetting a primary communications channel of a drone based on a new connection parameter received over a secondary communications channel are provided. It is detected that a drone is suspected of being hijacked. A primary communications channel to the drone that is used for flight operations is disabled. A secondary communications channel that is less suitable for flight control operations is established. At least one new connection parameter for the primary communications channel is received over the secondary communications channel. The primary communications channel is reset based on the at least one new connection parameter.
A surface mountable camera (1000) includes a junction box (104) and clip (300) that provide for a plurality of selectable mounting positions, each accommodating a hanging camera position. The junction box (104) provides a four-sided interior compartment, wherein at least three side walls of the compartment each include a slot (112) and an anchor feature (114) corresponding to the slot. The clip (300) is configured to interchangeably insert onto any of the three side walls of the junction box. The clip (300) includes an access port (304) formed therein for engaging with the anchor feature (114) of the junction box (104), and the clip includes first and second engagement tabs (302) for engaging into the slot (112) of the junction box (104). Once the clip (300) is anchored to the junction box (104), a camera assembly (200) is pivotably mounted, via a hinged bracket (400), to the clip of the junction box.
A surface mountable camera (1000) includes a junction box (104) and clip (300) that provide for a plurality of selectable mounting positions, each accommodating a hanging camera position. The junction box (104) provides a four-sided interior compartment, wherein at least three side walls of the compartment each include a slot (112) and an anchor feature (114) corresponding to the slot. The clip (300) is configured to interchangeably insert onto any of the three side walls of the junction box. The clip (300) includes an access port (304) formed therein for engaging with the anchor feature (114) of the junction box (104), and the clip includes first and second engagement tabs (302) for engaging into the slot (112) of the junction box (104). Once the clip (300) is anchored to the junction box (104), a camera assembly (200) is pivotably mounted, via a hinged bracket (400), to the clip of the junction box.
A security ecosystem, device and method for controlling workflows associated with different entities based on export and import rules is provided. For example, a computing device monitors execution of a first safety workflow, associated with a first entity, comprising a first trigger and a first responsive action. The computing device compares an event, associated with the first trigger, with an export rule. In response to the event of the first safety workflow meeting the export rule, the computing device compares the event with an import rule, associated with a second entity, for initiating a second safety workflow based on the event and associated with the second entity. In response to the event meeting the import rule, the computing device initiates the second safety workflow associated with the second entity, the second safety workflow comprising a second trigger and a second responsive action, the second trigger corresponding to the event.
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
A voice intercom system and method therefor are disclosed. The method includes wirelessly transmitting intercom directory data to a smartphone. The intercom directory data facilitates generation, on the smartphone, of an intercom access directory interface having a plurality of call initiation selection options, each with respect to which a call to a respective call recipient can be attempted.
H04N 7/18 - Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
G06K 19/06 - Record carriers for use with machines and with at least a part designed to carry digital markings characterised by the kind of the digital marking, e.g. shape, nature, code
H04L 61/4594 - Address books, i.e. directories containing contact information about correspondents
H04M 19/04 - Current supply arrangements for telephone systems providing ringing current or supervisory tones, e.g. dialling tone or busy tone the ringing-current being generated at the substations
A voice intercom system and method therefor are disclosed. The method includes wirelessly transmitting intercom directory data to a smartphone. The intercom directory data facilitates generation, on the smartphone, of an intercom access directory interface having a plurality of call initiation selection options, each with respect to which a call to a respective call recipient can be attempted.
A method and apparatus for volume control of an electronic device is provided herein. During operation, a volume-control knob will increase a volume of sound output from a device in a substantially linear fashion (versus knob rotation angle) as a volume-control knob is rotated. Once the volume-control knob is rotated past a predetermined amount, a volume boost is activated, increasing the volume level in a non-linear fashion. More particularly, in one embodiment of the present invention, once the volume-control knob is rotated past the predetermined amount (e.g., 300 degrees), the volume will be increased instantaneously (e.g., by 25%).
G10L 21/0216 - Noise filtering characterised by the method used for estimating noise
H04R 1/40 - Arrangements for obtaining desired frequency or directional characteristics for obtaining desired directional characteristic only by combining a number of identical transducers
One example device may be configured to determine that a destination public safety answering point (PSAP) of a received first call operates in a legacy PSAP domain. In response such a determination, the device may determine whether the first call is of a first type of call that includes an original number identification or of a second type of call that does not include an original number identification. In response to determining that the first call is of the first type, the device may deliver the first call to the destination PSAP along with an original number identification of the first call. In response to determining that the first call is of the second type, the device may generate a crafted number identification for the first call, and deliver the first call to the destination PSAP along with the crafted number identification.
A method and apparatus for volume control of an electronic device is provided herein. During operation, a volume-control knob will increase a volume of sound output from a device in a substantially linear fashion (versus knob rotation angle) as a volumecontrol knob is rotated. Once the volume-control knob is rotated past a predetermined amount, a volume boost is activated, increasing the volume level in a non-linear fashion. More particularly, in one embodiment of the present invention, once the volume-control knob is rotated past the predetermined amount (e.g., 300 degrees), the volume will be increased instantaneously (e.g., by 25%).
A method and apparatus for performing noise suppression on an electronic device is provided herein. During operation, a volume-control knob will increase a volume of sound output from a device in a substantially linear fashion (versus knob rotation angle) as a volume-control knob is rotated in a first direction. Noise suppression on the electronic device will also increase as the volume-control knob is rotated in the first direction.
G01B 7/30 - Measuring arrangements characterised by the use of electric or magnetic techniques for measuring angles or tapersMeasuring arrangements characterised by the use of electric or magnetic techniques for testing the alignment of axes
G05G 1/10 - Details, e.g. of discs, knobs, wheels or handles
Examples provide a video security system including an electronic processor configured to detect an anomaly by obtaining video data captured using an image sensor and determining a number of people detected in each of a plurality of frames of the video data. For each moment t, the electronic processor determines an average number of people n over a time interval (t−Δt1, t), where Δt1 is greater than or equal to the moment t. For each non-overlapping time interval Δt1, the electronic processor updates a histogram based on the average number of people for the time interval Δt1. In response to determining, using the histogram, that the probability ρ of the average number of people n over the time interval (t−Δt1, t) is less than a threshold probability ρ*, the electronic processor generates an alert indicating that an anomalous crowd size is detected.
G06V 10/34 - Smoothing or thinning of the patternMorphological operationsSkeletonisation
G06V 10/50 - Extraction of image or video features by performing operations within image blocksExtraction of image or video features by using histograms, e.g. histogram of oriented gradients [HoG]Extraction of image or video features by summing image-intensity valuesProjection analysis
G06V 20/40 - ScenesScene-specific elements in video content
G06V 20/52 - Surveillance or monitoring of activities, e.g. for recognising suspicious objects
G08B 31/00 - Predictive alarm systems characterised by extrapolation or other computation using updated historic data
Examples provide a video security system including an electronic processor configured to detect an anomaly by obtaining video data captured using an image sensor and determining a number of people detected in each of a plurality of frames of the video data. For each moment t, the electronic processor determines an average number of people n over a time interval (t-Δt1, t), where Δt1 is greater than or equal to the moment t. For each non-overlapping time interval Δt1, the electronic processor updates a histogram based on the average number of people for the time interval Δt1. In response to determining, using the histogram, that the probability ρ of the average number of people n over the time interval (t-Δt1, t) is less than a threshold probability ρ*, the electronic processor generates an alert indicating that an anomalous crowd size is detected.
Systems and method for camera calibration. In one example, the camera includes an electronic processor configured to obtain a bounding box in a captured image, the bounding box bounding a person in the image and having a lowermost vertical coordinate and an uppermost vertical coordinate. The electronic processor determines an initial estimation of values of a set of camera parameters Θ and a current estimation of values of the set of camera parameters Θ based on the initial estimation. The electronic processor iteratively updates the current estimation of values of the set of camera parameters Θ by determining feet coordinates within the bounding box, determining a vertical head coordinate, and updating the current estimation of values of the set of camera parameters Θ by reducing a difference between the vertical head coordinate and the uppermost vertical coordinate of the bounding box.
Examples provide a cloud server management controller configured to determine a network resource threshold and a cloud resource availability for a cloud server. The first resource availability is an amount of cloud network resources available in the cloud server within the network resource threshold. For each respective system of a plurality of local network systems, the controller determines a local resource usage and predicts a cloud resource requirement. The cloud resource requirement is an amount of cloud network resources required to provide a cloud-based equivalent of the respective system. The controller builds a model based on the cloud resource requirement for each respective system and the network resource threshold. The model defines a cloud migration priority for each of the plurality of local network systems. Based on the model, the controller generates a cloud migration timeline for sequentially migrating each respective system to the cloud server.
A method and apparatus for providing discovery within a D2D communications is provided herein. During operation, a first device will determine an identification of its own network slice, and an identification of a network slice other devices operate on. Only devices operating on the same network slice as the first device are allowed for D2D communication with the first device.
A method, system and computer program product for diagnosing a malfunctioning or misused electronic device is disclosed. The method includes performing analytics on at least one of video and audio to automatically detect at least one anomaly exhibited by the electronic device or exhibited in relation to user interaction with the electronic device, the at least one anomaly being distinguishable from other non-present anomalies detectable by a computer system that carries out the performing of the analytics.
A process for alerting a user for capturing digital evidence that is not in compliance with evidentiary policies. In operation, an electronic computing device acquires audio and/or video recordings from audio and/or video recorders operated by a user while the user is performing an assigned task. The device retrieves an evidentiary policy established corresponding to a particular type of the assigned task. The evidentiary policy identifies a list of evidentiary objects required to be digitally recorded in the audio and/or video recordings captured corresponding to the user's assigned task. If the audio and/or video recordings do not record at least one evidentiary object identified in the evidentiary policy with a specified quality level, then the device provides an electronic alert to the user indicating that the audio and/or video recordings are not in compliance with the evidentiary policy.
Device, system and method to control at least one electrical circuit to enter a low efficiency mode to heat a battery cell is provided. A temperature measurement device and battery cell parameter determination device respectively determine a temperature and impedance of a battery cell of a device. When the temperature of the battery cell is below a threshold temperature and the impedance of the battery cell is above a threshold impedance, a controller of the device controls at an electrical circuit of the device to enter a low efficiency mode by controlling the electrical circuit to draw an auxiliary current from the battery cell to heat the battery cell, the auxiliary current being below a given functional operating current of the electrical circuit, the electrical circuit having reduced functionality, relative to a given functionality when drawing a given functional operating current from the battery cell, while drawing the auxiliary current.
H01M 10/48 - Accumulators combined with arrangements for measuring, testing or indicating the condition of cells, e.g. the level or density of the electrolyte
62.
SECURITY ECOSYSTEM, DEVICE AND METHOD FOR COMMUNICATING WITH COMMUNICATION DEVICES BASED ON WORKFLOW INTERACTIONS
A device monitors execution of a safety workflow, the safety workflow comprising one or more triggers and one or more responsive actions. The device provides, at a display screen, an indication of the safety workflow and respective visual indications of: a physical sensor that generated sensor data of a trigger of the safety workflow; and a communication device associated with a responsive action to the trigger. The device detects, via an input device, an interaction with one or more of the respective visual indications to interact with one or more of the physical sensor and the communication device. Based on the interaction, the device one or more of: initiates communication with the communication device; and sends the sensor data to the communication device.
A process for redacting an image. In operation, an electronic computing device receives an image captured by a camera corresponding to a field of view of the camera. The image contains a plurality of pixels and each pixel in the plurality of pixels capturing a respective region in a plurality of regions of the field of view of the camera. The electronic computing device measures a distance from the camera to each respective region in the plurality of regions of the field of view of the camera. The electronic computing device redacts at least one pixel in the plurality of pixels contained in the image as a function of the distance measured from the camera to a respective region captured in the at least one pixel.
H04N 7/18 - Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
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
A process for redacting an image. In operation, an electronic computing device receives an image captured by a camera corresponding to a field of view of the camera. The image contains a plurality of pixels and each pixel in the plurality of pixels capturing a respective region in a plurality of regions of the field of view of the camera. The electronic computing device measures a distance from the camera to each respective region in the plurality of regions of the field of view of the camera. The electronic computing device redacts at least one pixel in the plurality of pixels contained in the image as a function of the distance measured from the camera to a respective region captured in the at least one pixel.
A method and apparatus for identifying a faked video is provided herein. During operation, when a video, or video call is received from a device, a simultaneous audio call is placed to the device (i.e., the video call and audio call take place simultaneously in time). The audio streams on both the video and audio call are compared, and a difference between the audio streams is identified. The video is deemed a potential fake if the difference between the audio streams is above a particular threshold.
A method and apparatus for minimizing a time that a camera field of view is not being monitored while the camera is undergoing a software or firmware update is provided herein. During operation a determination is made that a camera needs a software or firmware update. The location of a security asset (e.g., a mobile camera, a security guard, a drone, . . . , etc.) is determined. The update is performed based on the security asset being within a predetermined distance from the camera. More particularly, in one embodiment, the update is performed only when the security asset is within the predetermined distance from the camera.
A system for low earth orbit (LEO) satellite communication. In one example, the system includes a control computer and a workgroup including a plurality of communication devices. Each communication device includes an electronic processor configured to establish a wireless network connection with the control computer, determine connectivity data associated with a signal between the communication device and a first LEO satellite (121), and transmit the connectivity data to the control computer via the wireless network connection. The control computer is configured to receive the connectivity data from each communication device, and select a first one of the plurality of communication devices as a primary communication device (201) based on each of the connectivity data. The primary communication device (201) is configured to receive media from a different one of the plurality of communication devices via the wireless network connection and transmit the media to the first LEO satellite (121).
A method and apparatus for providing recommendations for evidence collection is provided herein. During operation a recommendation server is provided with evidence collected, including IoT device logs of events that can be used as evidence to investigate a particular crime. In response, the recommendation server will provide the investigator recommendations to search for additional evidence of events and objects that could potentially be used in a successful prosecution of the crime. The recommendations provided will be based on events that were used as evidence in past successful prosecutions of similar crimes.
A system and method for gradual migration from a legacy application to a replacement application is disclosed. The method includes determining whether or not a feature requested by a user is available amongst installed features currently deliverable by a replacement software application. When the feature requested by the user is currently deliverable by the replacement software application, a legacy software application communicates with the replacement software application to cause the feature requested by the user to be obtained from the replacement software application.
A process of selectively enabling execution of video analytics on videos captured by cameras. In operation, an electronic computing device accesses an incident database identifying incidents resolved by one or more agencies. The incidents include a first set of incidents that were first reported to the agencies by a human source and a second set of incidents that were first reported to the agencies by a video analytics system. The electronic computing device then estimates a first average cost incurred in resolving the first set of incidents and a second average cost incurred in resolving the second set of incidents. The electronic computing device enables the video analytics system to execute video analytics on videos captured by the one or more cameras to proactively detect and report incidents when the first average cost is higher than the second average cost by at least the predefined threshold.
A device, system, and method to provide front-facing camera images identified using a scene image assembled from rear-facing camera images is provided. A device retrieves dual-sensor camera images having respective metadata indicating image acquisitions substantially matching a time and a place associated with an incident, the dual-sensor camera images including a front and rear-facing camera image acquired via a same respective dual-sensor camera. The device assembles the rear-facing camera images into a scene image and renders the scene image at a display screen. The device receives an indication of a region-of-interest within the scene image and responsively: identifies a set of rear-facing camera images acquired within a predetermined threshold distance of the region-of-interest as determined using the respective metadata; and renders, at the display screen, front-facing camera images, from the dual-sensor camera images, associated with the set of rear-facing camera images acquired within the predetermined threshold distance of the region-of-interest.
A method, system and computer program product for backup assignment of a mobile electronics device is disclosed. In response to one or more device assignment requests received by a controller apparatus when a server is operating in an off-line mode, one or more device assignment records are created within the controller apparatus, and which indicate assignment of the at least one mobile electronics device to a respective one or more users. When the server is operating in an off-line mode such that communication between the controller apparatus and the server is off-line, the one or more device assignment records, in relation to the at least one mobile electronics device, are stored in the controller apparatus. In response to the server re-entering the on-line mode, the server is updated with the one or more device assignment records.
H04L 41/0853 - Retrieval of network configurationTracking network configuration history by actively collecting configuration information or by backing up configuration information
H04L 67/2869 - Terminals specially adapted for communication
73.
LOW EARTH ORBIT SATELLITE COMMUNICATION USING DEVICE DIVERSITY RECEPTION AND TRANSMISSION
A system for low earth orbit (LEO) satellite communication. In one example, the system includes a control computer and a workgroup including a plurality of communication devices. Each communication device includes an electronic processor configured to establish a wireless network connection with the control computer, determine connectivity data associated with a signal between the communication device and a first LEO satellite, and transmit the connectivity data to the control computer via the wireless network connection. The control computer is configured to receive the connectivity data from each communication device, and select a first one of the plurality of communication devices as a primary communication device based on each of the connectivity data. The primary communication device is configured to receive media from a different one of the plurality of communication devices via the wireless network connection and transmit the media to the first LEO satellite.
A method, system and computer program product for triggering an audio component change action is disclosed. The method includes analyzing audio corresponding to a period of time to identify one or more audio components of the audio that are matching to a defined set of feature parameters. The method also includes triggering an audio component change action on output of the audio, wherein effecting the audio component change action includes at least one of changing audio component volume and changing categorization of the one or more audio components, which may be based on NLP analyzation of preferences relating to volume and category of the one or more audio components.
A communication system and method provide for automatic arrestee grouping and action recommendation during a mass incident arrest. A portable radio sends a notification to a server indicating a mass incident event with grouping request for grouping arrestees. The server returns an electronic form including a mass arrest ID based on type of mass event. The electronic form facilitates collecting individual arrestee information based on the type of mass event. Current offense type and personal attribute information are collected and further electronically tagged to each arrestee. The server automatically assigns each arrestee to an offense group based on current offense type, and then refines the offense group into sub-groups based on prior arrest records. The server generates arrest processing procedure recommendations customized for each sub-group and transmits the recommendations to the PS radio associated with the grouping request.
A security camera and assembly include a camera lens assembly, a lens tilt locking mechanism, and a grab handle having LEDs mounted thereon. Embodiments include a lens tilt locking mechanism coupled to the camera lens assembly for setting a field of view (FOV) for a camera lens of the camera lens assembly. The grab handle is pivotally coupled to the camera lens assembly via a pivoting mechanism. The grab handle having LEDs mounted thereon pivots to provide independent control of illumination to the FOV without shifting the FOV. In a further embodiment, the grab handle may further include an antenna embedded therein.
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
H04N 23/56 - Cameras or camera modules comprising electronic image sensorsControl thereof provided with illuminating means
78.
METHOD AND APPARATUS FOR ASSIGNING A RELIABILITY SCORE FOR TIP SUBMISSIONS
A method and apparatus for providing a reliability score for a submitted tip is provided herein. During operation, when a user anonymously submits an image to a tipping server, the tipping server determines if an imager (e.g., a camera) used to capture the image has been used to capture any past images submitted to the tipping server. If so, a reliability score is determined for the imager that is based on a reliability of the past images submitted. The reliability score is then presented to any user viewing the image.
G06F 16/583 - Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
A security camera and assembly include a camera lens assembly, a lens tilt locking mechanism, and a grab handle having LEDs mounted thereon. Embodiments include a lens tilt locking mechanism coupled to the camera lens assembly for setting a field of view (FOV) for a camera lens of the camera lens assembly. The grab handle is pivotally coupled to the camera lens assembly via a pivoting mechanism. The grab handle having LEDs mounted thereon pivots to provide independent control of illumination to the FOV without shifting the FOV. In a further embodiment, the grab handle may further include an antenna embedded therein.
A holster for docking a portable radio is provided. The holster is configured with a GND extension path that provides an antenna counterpoise for an external antenna of the portable radio. The holster is formed of a housing (121) having a belt attachment element (122) extending therefrom and a GND contact (124) integrated into therein, the a GND contact for coupling to a corresponding radio GND of the docked radio. The GND extension path extends from GND contact (124) through a first conductive element (126) of the holster housing to a second conductive element (128) embedded in the belt attachment element of the holster.
Systems and methods for detecting security anomalies in a computing environment. One example system includes an electronic processor configured to receive, via the communication interface, security data for the computing environment and parse the security data to extract a feature set. The electronic processor is configured to apply noise to the feature set to produce a noised feature set and to produce a reduced noise feature set by processing the noised feature set using a neural network trained to remove noise. The electronic processor is configured to compare the reduced noise feature set to the feature set to determine a success score, select a threshold based on the security data, and determine whether the success score exceeds the threshold. The electronic processor is configured to, responsive to determining that the success score does not exceed the threshold, generate a security event based on the security data.
A method and apparatus for analyzing a dirty camera lens to determine if the dirty camera lens causes a failure to detect various events is provided herein. During operation, a filter is created that, when applied to previously-recorded video, mimics a dirty camera lens currently existing on a camera. The filter can then be applied to video taken previously with the camera as a result of an event being detected. The video analytics to detect the event are run again on the filtered video to see if the event is again detected. If the event was detected in both the filtered and unfiltered video, it is assumed that the particular event can still be detected even with the dirty lens. If the results differ, an alert can be sent to an operator indicating that the camera may no longer be capable of detecting the particular event.
A method and system for providing a fallback solution in a multi-tenant communication system is provided. A cloud-based call processing service receives a voice call initiation request from a first mobile device located at a first communication system. The voice call initiation request includes a request to complete a voice call with a second mobile device located at a second communication system. Resources are allocated at the first communication system and the second communication system. The cloud-based call processing service establishes a call between the first mobile device and the second mobile device. At some point the first communication system determines that it should fallback to single site operation. In fallback mode, call processing functionality is performed at the first communication system for the first mobile device.
A computer-implemented method comprises monitoring activity associated with a user, determining, by a trained machine learning model using the monitored activity of the user, that the user will need to access an asset that the user does not currently have access to, the machine learning model trained with a plurality of previous workflows completed by previous users and associated access privileges required for the previous workflows; and assigning an access privilege to the user, wherein the user is thereafter able to access to the asset.
A computer-implemented method comprises monitoring activity associated with a user; determining, by a trained machine learning model using the monitored activity of the user, that the user will need to access an asset that the user does not currently have access to, the machine learning model trained with a plurality of previous workflows completed by previous users and associated access privileges required for the previous workflows; and assigning an access privilege to the user, wherein the user is thereafter able to access to the asset.
An event detected in video is encoded as a binary vector. A set of binary vectors representative of the video may be so generated and stored in a queryable datastore. A query is encoded as a binary vector representative of a queried event. The query binary vector is compared to the set of binary vectors generated for the video and a result indicative of a similarity of the query binary vector to the set of binary vectors is returned.
A method and apparatus for operating a camera is provided herein. During operation a camera having pan/tilt/zoom (PTZ) capabilities will have its field of view (FOV) moved such that any detected blemish on the camera lies over an area with low activity (i.e., a low history of detected motion). More particularly, when it has been determined that a blemish or blemish resides on a camera's lens, a heat map of activity within the current FOV is determined. More active areas of the FOV are marked as “hot”, while less active areas of activity are marked as “cold”. The camera is then aligned such that the dirty portion of the lens does not align with any “hot” part of the heat map.
An event detected in video is encoded as a binary vector. A set of binary vectors representative of the video may be so generated and stored in a queryable datastore. A query is encoded as a binary vector representative of a queried event. The query binary vector is compared to the set of binary vectors generated for the video and a result indicative of a similarity of the query binary vector to the set of binary vectors is returned.
A security ecosystem, device, system and method for mitigating conflicts in workflows is provided. A computing device is provided having a network interface and a processor configured to receive workflows from a plurality of workflow computer systems and identify conflicts in the one or more physical devices that are shared among the workflows. The processor mitigates identified conflicts by modifying at least one of the workflows to avoid an identified conflict and provides the modified workflow back to one or more of workflow computer systems implementing the workflows that caused the conflicts.
Methods and systems for processing audio information to identify persons of interest in regard to a public-safety incident. An example method includes receiving human-generated narrative statements as audio and converting the narrative statements into corresponding digital texts. The method further includes determining incriminating scores for each of the narrative statements by identifying, in the digital texts, incident information classified as not being publicly known. The method further includes determining a cumulative score for an individual based on the incriminating scores tagged to the individual, making a determination of whether the individual is a person of interest based on a comparison of the cumulative score with a fixed threshold, and performing at least one automated responsive action based on the determination.
A device, system, and method for reducing machine learning bias in machine learning generated textual lists of time-stamped events is provided. The device generates, via a machine learning algorithm, using sensor data related to the incident, a textual list of time-stamped events for an incident, one or more of the events associated with respective machine learning confidence scores. For a given time-stamped event having a respective machine learning confidence score less than a threshold confidence score, the device redacts the given event in the list and replaces it in the list with a field for receiving input, the list of rendered at a display screen with the given event in the list replaced with the field. The device receives, via an input device, input at the field and after receiving the input, un-redacts the given event, and renders, at the display screen, the received input received and the given event.
A device, system, and method for an electronic response to a potential carjacking is provided. A device receives: a location and vehicle ignition status of a vehicle; and sensor data generated by one or more sensors that are onboard the vehicle, the sensor data different from the location and the vehicle ignition status. The device determines whether the location of the vehicle is associated with a carjacking type of location, and whether a combination of the vehicle ignition status and the sensor data meet a carjacking threshold condition. When both the location of the vehicle is associated with the carjacking type of location and the carjacking threshold condition is met, the device: outputs an alert at the vehicle indicative of, or associated with, the potential carjacking; and/or causes, a notification to be transmitted to a communication device associated with a public safety agency or a monitoring service.
B60R 25/102 - Fittings or systems for preventing or indicating unauthorised use or theft of vehicles actuating a signalling device a signal being sent to a remote location, e.g. a radio signal being transmitted to a police station, a security company or the owner
B60R 25/10 - Fittings or systems for preventing or indicating unauthorised use or theft of vehicles actuating a signalling device
B60R 25/30 - Detection related to theft or to other events relevant to anti-theft systems
B60R 25/31 - Detection related to theft or to other events relevant to anti-theft systems of human presence inside or outside the vehicle
B60R 25/33 - Detection related to theft or to other events relevant to anti-theft systems of global position, e.g. by providing GPS coordinates
An indication of a physical access action performed by a person in proximity of a camera determines a manner in which the physical access action is performed. An operational profile of the camera is set to control capture at the proximity of the camera based on the manner in which the physical access action is performed. This includes selecting the operational profile from a first operational profile and a second operational profile that is different from the first operational profile.
An analysis is performed on a request to compare a resource determined from the request with resources provided or needed by mobile physical entities, such as people, vehicles, or equipment. The analysis includes matching the request to a mobile physical entity. A target marking device that is associated with the mobile physical entity that matches the request is selected. A marking signal is transmitted to the target marking device to cause the target marking device to illuminate and thereby visually mark the mobile physical entity that matches the request.
An automatic gain control (AGC) attenuator for an amplifier. In one example, the AGC attenuator includes a first transistor stack including a plurality of first banks of current steering differential transistor pairs and configured to receive a radio frequency (RF) input signal and output a first attenuated RF signal. Each first bank of the plurality of first banks is configured to attenuate the RF input signal by a predetermined value. The AGC attenuator also includes a second transistor stack that includes a plurality of second banks of current steering differential transistor pairs. The second transistor stack is cascoded to the first transistor stack, and is configured to receive the first attenuated RF signal and output a second attenuated RF signal. Each second bank of the plurality of second banks is configured to attenuate the first attenuated RF signal by a predetermined value.
Methods and systems for tamper reduction for camera systems. One example system includes a camera with a first field of view configured to operate in a low-power mode and an active mode, an energy wave sensor with a second field of view, and an electronic processor. The electronic processor is configured to monitor, via the energy wave sensor, for an object within the second field of view and determine an object type of the object. In response to determining that the object type is a vehicle, the electronic processor transitions the camera from the low-power mode to the active mode and captures, via the camera, an image of the vehicle. In response to determining that the object type is a person, the electronic processor performs a tamper-monitoring action when the person is within a first predetermined range of a plurality of predetermined ranges of the system.
Imaging systems with an integrated infrared cut off filter and methods for operating same. One example system includes an image sensor and an electronic processor coupled to the image sensor. The image sensor includes a plurality of image recording pixels and a plurality of reserved pixels. A subset of the plurality of reserved pixels are covered by an infrared cut-off filter. The electronic processor is configured to determine a first visible light intensity for the subset of the plurality of reserved pixels. The electronic processor is further configured to control the image sensor to operate in one of a day mode and a night mode based on the first visible light intensity.
H04N 23/11 - Cameras or camera modules comprising electronic image sensorsControl thereof for generating image signals from different wavelengths for generating image signals from visible and infrared light wavelengths
G06V 10/143 - Sensing or illuminating at different wavelengths
G06V 10/74 - Image or video pattern matchingProximity measures in feature spaces
Methods and systems for processing audio information captured by an interactive virtual assistant (IVA). An example method includes: converting sound received by a microphone into electrical signals; generating voiceprints corresponding to voices represented in the electrical signals; distinguishing signals representing background speech and signals representing voice commands directed at the IVA; and based on various signals representing background speech and voice commands, labeling each of the voiceprints with a tag selected from the group consisting of an IVA interactor occupant tag, an IVA non-interactor occupant tag, and a non-occupant tag. The method also includes transmitting, in response to a trigger event, a message with at least one of an estimated number of occupants in a geofenced area corresponding to the IVA and an alert reporting an indication of unlawful activity thereat.
A mobile communication system that includes a short-range communication device, a mobile communication device, and a vehicle-based communication device configured to communicate with the short-range communication device. The system includes a sensor configured to generate sensor data and an electronic processor connected to the sensor and configured to receive sensor data that is associated with a scene external to a vehicle, detect an object based on the received sensor data, determine a parameter associated with the object based on the received sensor data and determine a communication interference value associated with the object based on the determined parameter. The electronic processor is also configured to pre-establish communication between the short-range communication device and the mobile communication device in response to determining that the communication interference value exceeds a pre-defined interference threshold.
Systems and methods for detecting and tracking conversations of interest in crowded areas. The system includes a plurality of body worn portable public safety communication devices, each including a plurality of microphones and an electronic processor. The electronic processor is configured to generate, using the plurality of microphones, a plurality of beams and scan in parallel, using the plurality of beams, a plurality of simultaneous audio conversations. The electronic processor is configured to identify and isolate a plurality of conversations of interest from among the audio conversations based on predetermined characteristics indicative of a potential threat. The electronic processor is configured to determine that at least two of the plurality of conversations of interest are potentially linked to a single potential threat, compile them for playback or transcription, and generate an alert indicating the availability of the linked conversations of interest.
G10L 15/18 - Speech classification or search using natural language modelling
G10L 25/51 - Speech or voice analysis techniques not restricted to a single one of groups specially adapted for particular use for comparison or discrimination
