SELF-OPTIMIZING VIDEO ANALYTICS PIPELINES

    公开(公告)号:US20220172005A1

    公开(公告)日:2022-06-02

    申请号:US17522226

    申请日:2021-11-09

    Abstract: A method for implementing a self-optimized video analytics pipeline is presented. The method includes decoding video files into a sequence of frames, extracting features of objects from one or more frames of the sequence of frames of the video files, employing an adaptive resource allocation component based on reinforcement learning (RL) to dynamically balance resource usage of different microservices included in the video analytics pipeline, employing an adaptive microservice parameter tuning component to balance accuracy and performance of a microservice of the different microservices, applying a graph-based filter to minimize redundant computations across the one or more frames of the sequence of frames, and applying a deep-learning-based filter to remove unnecessary computations resulting from mismatches between the different microservices in the video analytics pipeline.

    ECO: EDGE-CLOUD OPTIMIZATION OF 5G APPLICATIONS

    公开(公告)号:US20220150326A1

    公开(公告)日:2022-05-12

    申请号:US17515875

    申请日:2021-11-01

    Abstract: A method for optimal placement of microservices of a micro-services-based application in a multi-tiered computing network environment employing 5G technology is presented. The method includes accessing a centralized server or cloud to request a set of services to be deployed on a plurality of sensors associated with a plurality of devices, the set of services including launching an application on a device of the plurality of devices, modeling the application as a directed graph with vertices being microservices and edges representing communication between the microservices, assigning each of the vertices of the directed graph with two cost weights, employing an edge monitor (EM), an edge scheduler (ES), an alerts-manager at edge (AM-E), and a file transfer (FT) at the edge to handle partitioning of the microservices, and dynamically mapping the microservices to the edge or the cloud to satisfy application-specific response times.

    Online face clustering
    14.
    发明授权

    公开(公告)号:US11250244B2

    公开(公告)日:2022-02-15

    申请号:US16814453

    申请日:2020-03-10

    Abstract: Methods and systems for image clustering include matching a new image to a representative image of a cluster. The new image is set as a representative of the cluster with a first time limit. The new image is set as a representative of the cluster with a second time limit, responsive to a determination that the new image has matched at least one incoming image during the first time limit.

    Person search system based on multiple deep learning models

    公开(公告)号:US11250243B2

    公开(公告)日:2022-02-15

    申请号:US16808983

    申请日:2020-03-04

    Abstract: A computer-implemented method executed by at least one processor for person identification is presented. The method includes employing one or more cameras to receive a video stream including a plurality of frames to extract features therefrom, detecting, via an object detection model, objects within the plurality of frames, detecting, via a key point detection model, persons within the plurality of frames, detecting, via a color detection model, color of clothing worn by the persons, detecting, via a gender and age detection model, an age and a gender of the persons, establishing a spatial connection between the objects and the persons, storing the features in a feature database, each feature associated with a confidence value, and normalizing, via a ranking component, the confidence values of each of the features.

    Usecase specification and runtime execution

    公开(公告)号:US11249803B2

    公开(公告)日:2022-02-15

    申请号:US16809154

    申请日:2020-03-04

    Abstract: A computer-implemented method includes obtaining a usecase specification and a usecase runtime specification corresponding to the usecase. The usecase includes a plurality of applications each being associated with a micro-service providing a corresponding functionality within the usecase for performing a task. The method further includes determining that at least one instance of the at least one of the plurality of applications can be reused during execution of the usecase based on the usecase specification and the usecase runtime specification, and reusing the at least one instance during execution of the usecase.

    Distributed real-time security monitoring and alerting

    公开(公告)号:US11158176B2

    公开(公告)日:2021-10-26

    申请号:US16808722

    申请日:2020-03-04

    Abstract: Systems and methods are disclosed for distributed real-time security monitoring and alerting. The methods include transmitting a selected portion of biometrics data as a watchlist to each worker unit. The portion of biometrics data is selected in response to respective characteristic data received from each worker unit. Facial recognition data is received from each worker unit. The facial recognition data includes a person of interest with an associated match confidence value calculated by each worker unit based on respective watchlists received by each worker unit. A combined match confidence value is calculated between a same person of interest identified in multiple facial recognition data received from each worker unit and the biometric data associated with an individual. The combined match confidence value is calculated in response to match confidence values associated with the same person of interest in respective facial recognition data being below a match confidence threshold.

    Deep learning based tattoo detection system with optimized data labeling for offline and real-time processing

    公开(公告)号:US11113838B2

    公开(公告)日:2021-09-07

    申请号:US16814248

    申请日:2020-03-10

    Abstract: A computer-implemented method executed by at least one processor for detecting tattoos on a human body is presented. The method includes inputting a plurality of images into a tattoo detection module, selecting one or more images of the plurality of images including tattoos with at least three keypoints, the at least three keypoints having auxiliary information related to the tattoos, manually labeling tattoo locations in the plurality of images including tattoos to create labeled tattoo images, increasing a size of the labeled tattoo images identified to be below a predetermined threshold by padding a width and height of the labeled tattoo images, training two different tattoo detection deep learning models with the labeled tattoo images defining tattoo training data, and executing either the first tattoo detection deep learning model or the second tattoo detection deep learning model based on a performance of a general-purpose graphical processing unit.

    DISTRIBUTED REAL-TIME SECURITY MONITORING AND ALERTING

    公开(公告)号:US20200294376A1

    公开(公告)日:2020-09-17

    申请号:US16808722

    申请日:2020-03-04

    Abstract: Systems and methods are disclosed for distributed real-time security monitoring and alerting. The methods include transmitting a selected portion of biometrics data as a watchlist to each worker unit. The portion of biometrics data is selected in response to respective characteristic data received from each worker unit. Facial recognition data is received from each worker unit. The facial recognition data includes a person of interest with an associated match confidence value calculated by each worker unit based on respective watchlists received by each worker unit. A combined match confidence value is calculated between a same person of interest identified in multiple facial recognition data received from each worker unit and the biometric data associated with an individual. The combined match confidence value is calculated in response to match confidence values associated with the same person of interest in respective facial recognition data being below a match confidence threshold.

    MULTI-FACTOR AUTHENTICATION FOR PHYSICAL ACCESS CONTROL

    公开(公告)号:US20200294339A1

    公开(公告)日:2020-09-17

    申请号:US16809147

    申请日:2020-03-04

    Abstract: Methods and systems for authentication include determining, at a first worker system, that a master system that stores a current authentication-list cannot be reached by a first network. Authentication is performed on an authentication request using a previously stored copy of the authentication-list at the first worker system. The authentication includes facial recognition that is performed on detected face images for a first time window, before receiving the authentication request, and for a second time window, after receiving the authentication request. Authentication removes matching detected face images after completing an authentication request to prevent other individuals from using a same identifier. Access is granted to a secured area responsive to the authentication.

Patent Agency Ranking