SYSTEMS AND METHODS FOR SELECTING IMAGES

    公开(公告)号:US20210035281A1

    公开(公告)日:2021-02-04

    申请号:US17075957

    申请日:2020-10-21

    Applicant: GoPro, Inc.

    Abstract: A video may include multiple video frames. The video frames may be scored based on values of multiple content metrics for individual frames. One or more portions of the video that includes a threshold number of consecutive video frames that meet a score threshold may be identified. For individual ones of the identified portion(s), a video frame may be selected based on a maximum of the score for presentation as an exemplar image.

    AUTOMATED CAMERA MODE SELECTION USING LOCAL MOTION VECTOR

    公开(公告)号:US20210075965A1

    公开(公告)日:2021-03-11

    申请号:US16561811

    申请日:2019-09-05

    Applicant: GoPro, Inc.

    Abstract: Automated camera mode selection using local motion vectors is described. An image capture device includes an image metric estimation unit to detect a presence or level of an image metric in a scene of an image to capture based on image metric inputs, a motion estimation unit to determine a level of movement within the scene using ratios of histograms based on local motion vectors, a mode selection unit to select a camera mode for capturing the image based on outputs of the image metric estimation unit and the motion estimation unit, and an image sensor to capture the image according to the selected camera mode. The motion estimation unit computes a norm for each local motion vector, generates a histogram from the computed norms, determines movement metrics based on the ratios of histograms associated with different norm thresholds, and identifies the level of movement based on the movement metrics.

    Systems and methods for selecting images

    公开(公告)号:US11379965B2

    公开(公告)日:2022-07-05

    申请号:US17075957

    申请日:2020-10-21

    Applicant: GoPro, Inc.

    Abstract: A video may include multiple video frames. The video frames may be scored based on values of multiple content metrics for individual frames. One or more portions of the video that includes a threshold number of consecutive video frames that meet a score threshold may be identified. For individual ones of the identified portion(s), a video frame may be selected based on a maximum of the score for presentation as an exemplar image.

    Automated camera mode selection using local motion vector

    公开(公告)号:US11153485B2

    公开(公告)日:2021-10-19

    申请号:US16561811

    申请日:2019-09-05

    Applicant: GoPro, Inc.

    Abstract: Automated camera mode selection using local motion vectors is described. An image capture device includes an image metric estimation unit to detect a presence or level of an image metric in a scene of an image to capture based on image metric inputs, a motion estimation unit to determine a level of movement within the scene using ratios of histograms based on local motion vectors, a mode selection unit to select a camera mode for capturing the image based on outputs of the image metric estimation unit and the motion estimation unit, and an image sensor to capture the image according to the selected camera mode. The motion estimation unit computes a norm for each local motion vector, generates a histogram from the computed norms, determines movement metrics based on the ratios of histograms associated with different norm thresholds, and identifies the level of movement based on the movement metrics.

    Systems and methods for selecting images

    公开(公告)号:US10817998B1

    公开(公告)日:2020-10-27

    申请号:US16233870

    申请日:2018-12-27

    Applicant: GoPro, Inc.

    Abstract: A video may include multiple video frames. The video frames may be scored based on values of multiple content metrics for individual frames. One or more portions of the video that includes a threshold number of consecutive video frames that meet a score threshold may be identified. For individual ones of the identified portion(s), a video frame may be selected based on a maximum of the score for presentation as an exemplar image.

Patent Agency Ranking