Systems and methods for personalized intent prediction

    公开(公告)号:US11205314B2

    公开(公告)日:2021-12-21

    申请号:US15930848

    申请日:2020-05-13

    Abstract: Systems for personalized intent prediction may perform a process including receiving image data depicting the behavior of a person on approach toward a secure location, generating intent data including data representing a current trajectory of the person on the current approach, comparing the intent data with a personal statistical model for the person that includes data representing trajectories associated with historical approaches by the person toward the secure location and respective result data indicating whether the historical approach resulted in the person entering the secure location, determining, dependent on the comparing, a personalized intent score representing a likelihood that the person intends to enter the secure location on the current approach, and pre-emptively enabling, or refraining from pre-emptively enabling, entry to the secure location prior to the person reaching the secure location based on whether the personalized intent score meets or exceeds a predetermined minimum confidence threshold for enabling entry.

    Method and apparatus for distributed edge learning

    公开(公告)号:US11144796B2

    公开(公告)日:2021-10-12

    申请号:US16654375

    申请日:2019-10-16

    Abstract: An object learning system, method, and device. The object learning device includes an electronic processor configured to provide an identifier based on target to at least one auxiliary object learning device and initiate an edge learning process on the target to create first preprocessed object recognition data. The electronic processor is further configured to receive second preprocessed object recognition data corresponding to the target from the at least one auxiliary object learning device and create, based on the first and the second preprocessed object recognition data, a classifier of the target.

    Device, system and method for generating an alert and an automatic search for a candidate subject

    公开(公告)号:US11036979B2

    公开(公告)日:2021-06-15

    申请号:US15922452

    申请日:2018-03-15

    Abstract: A device, system and method for generating an alert and an automatic search for a candidate subject is provided. The device monitors one or more data sources to identify a candidate subject. The device determines, from rules for rating candidate subjects stored in a memory, a rating of the candidate subject. When the rating meets a first threshold: the device transmits, to one or more communication devices, an alert identifying the candidate subject. When the rating meets a second threshold, lower than the first threshold: the devices provides, a classifier defining the candidate subject to an object recognition engine to cause the object recognition engine to automatically search for the candidate subject, using the classifier, in multimedia data received at one or more edge devices. The multimedia data may include images.

    Systems and methods for inline object detection using a hue saturation value

    公开(公告)号:US10360478B2

    公开(公告)日:2019-07-23

    申请号:US15622724

    申请日:2017-06-14

    Abstract: A system and method for inline object detection using hue saturation value. One method includes determining, with an electronic processor running a single object classifier, a hue saturation value range. The method includes receiving a digital image including an object. The method includes detecting, without reloading the single object classifier, a macroblock from the digital image, the macroblock associated with the object. The method includes determining a target region within the macroblock. The method includes determining a quantity of pixels in the target region having a hue saturation value within the hue saturation value range. The method includes, when the quantity of pixels exceeds a threshold, completing object classification of the macroblock.

    METHOD AND APPARATUS FOR DISTRIBUTED EDGE LEARNING

    公开(公告)号:US20190042896A1

    公开(公告)日:2019-02-07

    申请号:US15668624

    申请日:2017-08-03

    Abstract: An object learning system, method, and device. The object learning device includes an electronic processor configured to provide an identifier based on target to at least one auxiliary object learning device and initiate an edge learning process on the target to create first preprocessed object recognition data. The electronic processor is further configured to receive second preprocessed object recognition data corresponding to the target from the at least one auxiliary object learning device and create, based on the first and the second preprocessed object recognition data, a classifier of the target.

    Method and system for tracking a plurality of communication devices

    公开(公告)号:US10149110B2

    公开(公告)日:2018-12-04

    申请号:US15535351

    申请日:2016-06-06

    Abstract: Method and system for tracking a plurality of communication devices. One system includes a plurality of communication devices that each include a respective electronic processor, a respective camera, a respective location component, and a respective network interface. At least one of the plurality of communication devices is configured to receive location information from each of the other of the plurality of communication devices, generate a tracking map, and transmit the tracking map to each of the other of the plurality of communication devices. The tracking map assigns each of the plurality of communication devices only one of the other of the plurality of communication devices. Each of the plurality of communication devices is configured to control, with its respective electronic processor, its respective camera based on the tracking map to include in its field of view its respectively assigned one of the other of the plurality of communication devices.

Patent Agency Ranking