Image selection apparatus, image selection method, and non-transitory computer-readable medium

    公开(公告)号:US12174885B2

    公开(公告)日:2024-12-24

    申请号:US17923705

    申请日:2020-05-14

    Abstract: A query acquisition unit (610) acquires pose information (hereinafter, described as query pose information) that is information to be a query and indicates a pose of a person. A search information acquisition unit (620) acquires a plurality of pieces of search pose information. The search pose information is pose information about an image (hereinafter, described as a target image) to be a search target, and is stored in a database by a plurality of target images. A selection unit (630) selects, from among the plurality of pieces of search pose information, two or more pieces of the search pose information whose degree of similarity to the query pose information satisfies a reference. The selection processing becomes substantially processing of selecting a target image similar to an image (hereinafter, described as a query image) associated with the query pose information.

    MOTION DETERMINATION APPARATUS, MOTION DETERMINATION METHOD, AND NON-TRANSITORY COMPUTER READABLE MEDIUM

    公开(公告)号:US20240420506A1

    公开(公告)日:2024-12-19

    申请号:US18703754

    申请日:2022-03-02

    Abstract: Provided is a motion determination apparatus and the like that can determine a motion of a person faster and more efficiently. A motion determination apparatus includes a position specifying means for specifying a position of a person from acquired image data, a motion specifying means for specifying a first characteristic motion by analyzing a motion of the person in the image data in accordance with a first characteristic motion pattern associated with a first position of the specified person, and specifying a second characteristic motion by analyzing a motion of the person in the image data in accordance with a second characteristic motion pattern associated with a second position of the specified person, and a determination means for determining whether the specified characteristic motion is in a predetermined order.

    Three-dimensional person behavior estimation

    公开(公告)号:US12118741B2

    公开(公告)日:2024-10-15

    申请号:US17617431

    申请日:2019-06-13

    CPC classification number: G06T7/70 G06V10/82 G06V20/52 G06V40/10

    Abstract: The present invention provides a processing apparatus (20) including a first generation unit (22) that generates, from a plurality of time-series images, three-dimensional feature information indicating a time change of a feature in each position in each of the plurality of images, a second generation unit (23) that generates person position information indicating a position in which a person is present in each of the plurality of images, and an estimation unit (24) that estimates person behavior indicated by the plurality of images, based on the time change of the feature indicated by the three-dimensional feature information in the position in which the person is present being indicated by the person position information.

    Retrieval device, control method, and non-transitory storage medium

    公开(公告)号:US11749021B2

    公开(公告)日:2023-09-05

    申请号:US17610200

    申请日:2020-05-08

    CPC classification number: G06V40/171 G06V10/761 G06V10/771 G06V10/7715

    Abstract: A retrieval apparatus (2000) is accessible to a storage region (50) in which a plurality of pieces of object information (100) are stored. The object information (100) includes a feature value set (104) being a set of a plurality of feature values acquired regarding an object. The retrieval apparatus (2000) acquires a feature value set (retrieval target set (60)) being a retrieval target, and determines the object information (100) having the feature value set (104) similar to the retrieval target set (60) by comparing the retrieval target set (60) with the feature value set (104). Herein, in a case where a feature value set satisfies a predetermined condition, the retrieval apparatus (2000) performs comparison between the feature value set and another feature value set by using a part of feature values within the feature value set. Further, the retrieval apparatus (2000) outputs output information relating to the determined object information (100).

    Index generation apparatus and index generation method

    公开(公告)号:US10437803B2

    公开(公告)日:2019-10-08

    申请号:US15325270

    申请日:2015-03-12

    Inventor: Jianquan Liu

    Abstract: An index generation apparatus includes: an index generation unit generating the index including a lower node and an upper node by using a degree of similarity between pieces of data, the upper node including an entry having a link relationship with the lower node and indicating representative data, the representative data having the degree of similarity with respect to data indicated by the entry of the lower node that is equal to or greater than a similarity degree threshold value given to the link relationship; and a threshold value determination unit determining a default similarity degree threshold value and an adjustment value with respect to each link relationship between the upper node and the lower node, and determining each similarity degree threshold value to be given to each link relationship by subtracting the adjustment value from the default similarity degree threshold value.

    ACTION LOCALIZATION APPARATUS, CONTROL METHOD, AND NON-TRANSITORY COMPUTER-READABLE STORAGE MEDIUM

    公开(公告)号:US20250054339A1

    公开(公告)日:2025-02-13

    申请号:US18723644

    申请日:2022-01-06

    Abstract: An action localization apparatus acquires a target clip and detects persons from the target clip. The action localization apparatus generates a person clip from the target clip for each of the persons detected from the target clip, and extracts a feature map from each of the person clip. The action localization apparatus computes, for each of predefined action classes, an action score that indicates confidence of an action of that action class being included in the target clip based on the feature maps extracted from the person clips, and localizes each action whose action class has the action score larger than or equal to a threshold by performing class activation mapping on each of the person clips.

Patent Agency Ranking