METHOD, SYSTEM AND COMPUTER READABLE MEDIUM FOR INTEGRATION AND AUTOMATIC SWITCHING OF CROWD ESTIMATION TECHNIQUES

    公开(公告)号:US20210012506A1

    公开(公告)日:2021-01-14

    申请号:US16980726

    申请日:2019-02-27

    Abstract: Methods and systems for crowd level estimation are provided. The system includes a plurality of performance modeling modules (206), an input module (202) and a crowd estimation technique integration module. The plurality of performance modeling modules (206) performance model each of a plurality of crowd estimation techniques based on an accuracy thereof at different crowd levels and/or at different locations. The input module (202) receives an image of a crowd. The crowd estimation technique integration module (208) selects one or more of the plurality of crowd estimation techniques in response to the performance modeling of the one or more of the plurality of crowd estimation techniques and an estimated crowd level and/or an estimated location. The crowd estimation technique integration module (208) then estimates a crowd count of the crowd in the received image in accordance with the selected one or more of the plurality of crowd estimation techniques.

    METHOD AND SYSTEM FOR IDENTIFYING AN INDIVIDUAL IN A CROWD

    公开(公告)号:US20210049369A1

    公开(公告)日:2021-02-18

    申请号:US16968640

    申请日:2019-03-08

    Abstract: The present disclosure relates to methods and systems for identifying an individual in a crowd. The method comprises the steps of capturing a plurality of crowd-viewing images using multiple image-capturing devices. For each image, a reference point within a facial contour of a person in the image is selected. The reference point is selected based on a facial feature on the facial contour of the person. The method further comprises the step of processing the image to obtain one or more angular measurements associated with a posture displayed by the person in the image. Based on the obtained angular measurements, location data of a predetermined body point of the person relative to the reference point is extracted.

Patent Agency Ranking