Appearance presentation system, method, and program

    公开(公告)号:US09811738B2

    公开(公告)日:2017-11-07

    申请号:US14649312

    申请日:2013-11-29

    Inventor: Hiroo Ikeda

    Abstract: An appearance presentation system is provided. The appearance presentation system can present the appearance of an object to be monitored at a position that the user designates in an image such that the user can previously grasp the extent to which the image to be captured with a camera is suitable for an image recognition process. A display control unit 10 displays, on a display device, an image obtained by superimposing an object indicator indicating the object to be monitored on an image to be captured when the camera of which position and posture are determined shoots a predetermined region to be monitored. A position designation reception unit 4 receives the designation of the position of the object indicator in the image. An image generation unit 3 generates an image to be captured when the camera shoots a state in which the object to be monitored is placed at a position that is in the region to be monitored and that corresponds to the position designated in the image. Then, the display control unit 10 extracts a part corresponding to the object to be monitored from the image generated in the image generation unit 3, and displays the part on the display device.

    TIME SYNCHRONIZATION INFORMATION COMPUTATION DEVICE, TIME SYNCHRONIZATION INFORMATION COMPUTATION METHOD AND TIME SYNCHRONIZATION INFORMATION COMPUTATION PROGRAM
    32.
    发明申请
    TIME SYNCHRONIZATION INFORMATION COMPUTATION DEVICE, TIME SYNCHRONIZATION INFORMATION COMPUTATION METHOD AND TIME SYNCHRONIZATION INFORMATION COMPUTATION PROGRAM 有权
    时间同步信息计算设备,时间同步信息计算方法和时间同步信息计算程序

    公开(公告)号:US20140313413A1

    公开(公告)日:2014-10-23

    申请号:US14366137

    申请日:2012-11-15

    CPC classification number: H04N5/06 G08B13/19602 G08B13/19645 H04N5/23254

    Abstract: To provide a time synchronization information computation device capable of synchronizing the times of a plurality of cameras without the need of a special device, a time synchronization information computation method and a time synchronization information computation program. There are provided a plurality of video acquisition means 100-1 to 100-N for acquiring videos, a plurality of visual event detection means 101-1 to 101-N provided corresponding to the plurality of video acquisition means for analyzing the videos acquired by the plurality of video acquisition means 100-1 to 100-N to detect visual events, and generating visual event detection information including time information on when the visual events occur, and visual event integration means 102 for integrating the visual event detection information generated by the plurality of visual event detection means 101-1 to 101-N and synchronizing the times of the videos acquired by the plurality of video acquisition means 100-1 to 100-N.

    Abstract translation: 提供能够在不需要专用设备的情况下同步多个摄像机的时间的时间同步信息计算装置,时间同步信息计算方法和时间同步信息计算程序。 提供了用于获取视频的多个视频获取装置100-1至100-N,与多个视频获取装置相对应地提供的多个视觉事件检测装置101-1至101-N,用于分析由 多个视频获取装置100-1至100-N,用于检测视觉事件,以及生成视觉事件检测信息,包括关于视觉事件何时发生的时间信息;以及视觉事件整合装置102,用于对由多个视觉事件产生的视觉事件检测信息进行积分 的视觉事件检测装置101-1至101-N,并且使由多个视频获取装置100-1至100-N获取的视频的时间同步。

    Information processing apparatus, control method, and non-transitory storage medium

    公开(公告)号:US12154365B2

    公开(公告)日:2024-11-26

    申请号:US18232215

    申请日:2023-08-09

    Inventor: Hiroo Ikeda

    Abstract: An information processing apparatus (2000) includes a recognizer (2020). An image (10) is input to the recognizer (2020). The recognizer (2020) outputs, for a crowd included in the input image (10), a label (30) describing a type of the crowd and structure information (40) describing a structure of the crowd. The structure information (40) indicates a location and a direction of an object included in the crowd. The information processing apparatus (2000) acquires training data (50) which includes a training image (52), a training label (54), and training structure information (56). The information processing apparatus (2000) performs training of the recognizer (2020) using the label (30) and the structure information (40), which are acquired by inputting the training image (52) with respect to the recognizer (2020, and the training label (54) and the training structure information (56).

    IMAGE PROCESSING APPARATUS, IMAGE PROCESSING METHOD, AND NON-TRANSITORY STORAGE MEDIUM

    公开(公告)号:US20240070870A1

    公开(公告)日:2024-02-29

    申请号:US18234172

    申请日:2023-08-15

    Inventor: Hiroo Ikeda

    CPC classification number: G06T7/11 G06T7/70 G06T2207/10016

    Abstract: To detect a stagnant object by an image analysis at high accuracy, the present invention provides an image processing apparatus 10 including: an acquisition unit 11 that acquires partial region information for each frame image, the partial region information indicating a situation of a target object in each of a plurality of partial regions within one image for each frame image; and an extraction unit 12 that extracts the partial region from a plurality of the partial regions, based on the partial region information for the each frame image, the partial region to be extracted satisfying at least one of a condition that presence of a plurality of the target objects continues at a predetermined level or higher and a condition that uniformity of a state of an aggregation constituted by a plurality of the target objects being present continues at a predetermined level or higher.

Patent Agency Ranking