Abstract

Systems and methods for loss prevention in a physical retail space are provided. In an embodiment, a method includes: generating plurality of registries as a customer moves about in the physical retail, each registry comprising a template characterizing the customer and a list of detected items; matching a first one of the plurality of registries with a second one of the plurality of registries based at least in part on the template; comparing the lists of items in the matched registries; and causing at least one downstream loss prevention action to be taken based on a comparison between the lists of items. A corresponding system and non-transitory computer-readable medium are also provided.

IPC Classes  ?

• G08B 13/00 - Burglar, theft or intruder alarms
• G08B 13/24 - Electrical actuation by interference with electromagnetic field distribution
• 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

Abstract

Computer-implemented methods for real-time analysis of video images are described. In an embodiment, the method includes receiving video images captured by at least one camera; detecting anonymous body regions of individuals in the video images by performing a body key point analysis on the video images using a first neural network; extracting subregions from the video images containing the anonymous body regions; and processing the extracted subregions using a second neural network to classify the anonymous body regions contained in the extracted subregions according to demographic information. Corresponding systems and non-transitory computer-readable media are also described.

IPC Classes  ?

• G06V 40/10 - Human or animal bodies, e.g. vehicle occupants or pedestriansBody parts, e.g. hands
• G06F 21/62 - Protecting access to data via a platform, e.g. using keys or access control rules
• 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

Abstract

A method for performing thermal screening is described. The method includes capturing at least one non-thermal image of a scene having a person; capturing at least one thermal image of the scene having the person; determining a region of interest of the non-thermal image; determining, based on a body sub-region of the non-thermal image corresponding to the body of the person within the scene, a distance value representative of a physical distance of the person from the thermal camera; determining a region of interest of the thermal image corresponding to the region of interest of the non-thermal image; determining a raw temperature value for the person based on the region of interest of the thermal image; and normalizing the raw temperature value based on at least the distance value to determine a normalized temperature value. A corresponding system and non-transitory computer-readable medium are also provided.

IPC Classes  ?

• A61B 5/01 - Measuring temperature of body parts
• A61B 5/00 - Measuring for diagnostic purposes Identification of persons
• G06T 7/00 - Image analysis
• G06T 7/20 - Analysis of motion
• G06T 7/50 - Depth or shape recovery
• G06V 10/143 - Sensing or illuminating at different wavelengths
• G06V 10/25 - Determination of region of interest [ROI] or a volume of interest [VOI]
• G06V 40/10 - Human or animal bodies, e.g. vehicle occupants or pedestriansBody parts, e.g. hands
• G06V 40/16 - Human faces, e.g. facial parts, sketches or expressions
• G16H 50/30 - ICT specially adapted for medical diagnosis, medical simulation or medical data miningICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for calculating health indicesICT specially adapted for medical diagnosis, medical simulation or medical data miningICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for individual health risk assessment
• 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
• H04N 23/13 - Cameras or camera modules comprising electronic image sensorsControl thereof for generating image signals from different wavelengths with multiple sensors

Abstract

Computer-implemented methods for real-time analysis of video images are described. In an embodiment, the method includes receiving video images captured by at least one camera; detecting anonymous body regions of individuals in the video images by performing a body key point analysis on the video images using a first neural network; extracting subregions from the video images containing the anonymous body regions; and processing the extracted subregions using a second neural network to classify the anonymous body regions contained in the extracted subregions according to demographic information. Corresponding systems and non-transitory computer-readable media are also described.

IPC Classes  ?

• G06N 3/0464 - Convolutional networks [CNN, ConvNet]
• G06N 3/08 - Learning methods
• G06Q 30/0201 - Market modellingMarket analysisCollecting market data
• 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

Abstract

Computer-implemented methods for real-time analysis of video images are described. In an embodiment, the method includes receiving video images captured by at least one camera; detecting anonymous body regions of individuals in the video images by performing a body key point analysis on the video images using a first neural network; extracting subregions from the video images containing the anonymous body regions; and processing the extracted subregions using a second neural network to classify the anonymous body regions contained in the extracted subregions according to demographic information. Corresponding systems and non-transitory computer-readable media are also described.

IPC Classes  ?

• G06V 20/40 - ScenesScene-specific elements in video content
• G06N 3/08 - Learning methods
• G06N 3/0464 - Convolutional networks [CNN, ConvNet]
• G06Q 30/0201 - Market modellingMarket analysisCollecting market data
• G06V 10/82 - Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
• G06V 20/52 - Surveillance or monitoring of activities, e.g. for recognising suspicious objects

Abstract

A method for performing thermal screening is described. The method includes capturing at least one non-thermal image of a scene having a person; capturing at least one thermal image of the scene having the person; determining a region of interest of the non-thermal image; determining, based on a body sub-region of the non-thermal image corresponding to the body of the person within the scene, a distance value representative of a physical distance of the person from the thermal camera; determining a region of interest of the thermal image corresponding to the region of interest of the non-thermal image; determining a raw temperature value for the person based on the region of interest of the thermal image; and normalizing the raw temperature value based on at least the distance value to determine a normalized temperature value. A corresponding system and non-transitory computer-readable medium are also provided.

IPC Classes  ?

• G01J 5/80 - Calibration
• G06V 10/25 - Determination of region of interest [ROI] or a volume of interest [VOI]
• G06V 40/10 - Human or animal bodies, e.g. vehicle occupants or pedestriansBody parts, e.g. hands
• G06V 40/16 - Human faces, e.g. facial parts, sketches or expressions
• G01J 5/70 - Passive compensation of pyrometer measurements, e.g. using ambient temperature sensing or sensing of temperature within housing

Abstract

A method and system for privacy-aware movement tracking includes receiving a series of images of a field of view, such as captured by a camera. The images containing movement of an unidentified person. A movement dataset for the unidentified person is generated based on tracking movement of the person over the field of view within the images. A characterizing feature set is determined for the unidentified person. The set is associated within the movement dataset to form a first track entry. Anonymizing of the body region of the unidentified person can be applied to remove identifying features while or prior to determining the characterizing feature set. A second track entry can be generated from a second series of images and a match between the track entries can be determined. A method and system for privacy-aware operation and learning of a computer-implemented classification module is also contemplated.

IPC Classes  ?

• G06T 7/246 - Analysis of motion using feature-based methods, e.g. the tracking of corners or segments
• G06F 21/60 - Protecting data
• G06K 9/78 - Combination of image acquisition and recognition functions
• G06N 20/00 - Machine learning
• G06N 3/02 - Neural networks
• G06N 3/08 - Learning methods
• G06T 5/00 - Image enhancement or restoration
• G06T 7/00 - Image analysis
• 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 21/80 - Generation or processing of content or additional data by content creator independently of the distribution processContent per se
• H04N 7/18 - Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast

Abstract

A method and system for privacy-aware movement tracking includes receiving a series of images of a field of view, such as captured by a camera. The images containing movement of an unidentified person within the field of view. A body region corresponding to the person is detected within the images. A movement dataset for the unidentified person is generated based on tracking movement of the body region over the fired of view within the images is generated. A characterizing feature set is determined for the unidentified person. The set is associated within the movement dataset to form a first track entry. Anonymizing of the body region can be applied to remove identifying features while or prior to determining the characterizing feature set. A second track entry can be generated from a second series of images and match between the track entries can be determined. A method and system for privacy-aware operation and learning of a computer-implemented classification module is also contemplated.

IPC Classes  ?

• G06F 21/60 - Protecting data
• G06F 16/73 - Querying
• 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
• G06F 21/62 - Protecting access to data via a platform, e.g. using keys or access control rules
• G06V 20/40 - ScenesScene-specific elements in video content
• G06V 20/52 - Surveillance or monitoring of activities, e.g. for recognising suspicious objects
• G06V 40/16 - Human faces, e.g. facial parts, sketches or expressions
• G06V 10/22 - Image preprocessing by selection of a specific region containing or referencing a patternLocating or processing of specific regions to guide the detection or recognition

Abstract

A system and method for performing distributed facial recognition divides processing steps between a user engagement device/robot, having lower processing power, and a remotely located server, having significantly more processing power. Images captured by the user engagement device/robot are processed at the device/robot by applying a first set of image processing steps that includes applying a first face detection. First processed images having at least one detected face is transmitted to the server, whereat a second set of image processing steps are applied to determine a stored user facial image matching the detected face of the first processed image. At least one user property associated to the given matching user facial image is then transmitted to the user engagement device/robot. An interactive action personalized to the user can further be performed at the user engagement device/robot.

IPC Classes  ?

• G06V 40/16 - Human faces, e.g. facial parts, sketches or expressions
• G06V 10/96 - Management of image or video recognition tasks
• G06V 10/98 - Detection or correction of errors, e.g. by rescanning the pattern or by human interventionEvaluation of the quality of the acquired patterns
• G06V 20/10 - Terrestrial scenes
• G06V 40/50 - Maintenance of biometric data or enrolment thereof

Abstract

A system and method for performing distributed facial recognition divides processing steps between a user engagement device/robot, having lower processing power, and a remotely located server, having significantly more processing power. Images captured by the user engagement device/robot are processed at the device/robot by applying a first set of image processing steps that includes applying a first face detection. First processed images having at least one detected face is transmitted to the server, whereat a second set of image processing steps are applied to determine a stored user facial image matching the detected face of the first processed image. At least one user property associated to the given matching user facial image is then transmitted to the user engagement device/robot. An interactive action personalized to the user can further be performed at the user engagement device/robot.

IPC Classes  ?

• G06K 9/78 - Combination of image acquisition and recognition functions
• G06F 15/16 - Combinations of two or more digital computers each having at least an arithmetic unit, a program unit and a register, e.g. for a simultaneous processing of several programs
• G06K 9/36 - Image preprocessing, i.e. processing the image information without deciding about the identity of the image
• G06K 9/62 - Methods or arrangements for recognition using electronic means
• G06N 20/00 - Machine learning
• B25J 9/18 - Programme controls electric