公开(公告)号：US20240290034A1

公开(公告)日：2024-08-29

申请号：US18563719

申请日：2021-11-17

Applicant: Intel Corporation

Inventor： Longwei Fang ,  Yikai Fang ,  Hongzhi Tao ,  Qiang Li ,  Hang Zheng

IPC: G06T17/00 ,  G06T7/246 ,  G06T7/292 ,  G06T7/73 ,  G06T19/20

CPC classification number: G06T17/00 ,  G06T7/251 ,  G06T7/292 ,  G06T7/75 ,  G06T19/20 ,  G06T2207/30196 ,  G06T2207/30221 ,  G06T2219/2004

Abstract: A method and system of multi-view image processing with accurate skeleton reconstruction uses joint confidence values.

公开(公告)号：US20240005701A1

公开(公告)日：2024-01-04

申请号：US18254818

申请日：2021-09-23

Applicant: Intel Corporation

Inventor： Chenning Liu ,  Qiang Li ,  Wenlong Li ,  Yikai Fang ,  Hang Zheng ,  Jiansheng Chen

IPC: G06V40/20 ,  G06V10/82 ,  G06V10/764

CPC classification number: G06V40/23 ,  G06V10/764 ,  G06V10/82

Abstract: An example apparatus includes processor circuitry to extract features from image data obtained from a plurality of cameras, the extraction of features performed using a plurality of sequential neural network layers; in response to each of the plurality of sequential neural network layer extracting the features, identify the extracted features in a torso region of the image data via a plurality of attention modules; estimate body landmarks from image data to localize an area; generate an upper heatmap mask based on a geometric center of the image data; calculate a loss function for the image data based on a cross-entropy loss, a pixel-wise loss, and a triplet loss determined from the extracted features and the generated heatmap mask; select lowest correlated classes based on calculated correlations between pairs of a plurality of classes; and calculate voting scores for groups associated with the lowest correlated classes.

公开(公告)号：US20220180649A1

公开(公告)日：2022-06-09

申请号：US17438348

申请日：2019-07-31

Applicant: Intel Corporation

Inventor： Qiang Li ,  Wenlong Li ,  Chen Ling ,  Hang Zheng

IPC: G06V20/62 ,  G06T7/73 ,  G06V10/764 ,  G06V10/22 ,  G06V10/44 ,  G06V20/70 ,  G06V10/82 ,  G06V40/10

Abstract: A method is described herein. The method includes the designation of a player as a profile player or a non-profile player in each camera view. In response to the player being a non-profile player, the method includes extracting features from the detected player within the bounding box and classifying the features according to a label. In response to the player being a non-profile player, the method also includes selecting a label with a highest number of votes according to a voting policy as a final label.

公开(公告)号：US20220198684A1

公开(公告)日：2022-06-23

申请号：US17435923

申请日：2019-07-31

Applicant: Intel Corporation

Inventor： Yikai Fang ,  Qiang Li ,  Wenlong Li ,  Chenning Liu ,  Chen Ling ,  Hongzhi Tao ,  Yumeng Wang ,  Hang Zheng

IPC: G06T7/292 ,  G06T7/70 ,  G06T15/20 ,  A63F13/213 ,  A63F13/42 ,  A63F13/65

Abstract: A method for trajectory generation based on player tracking is described herein. The method includes determining a temporal association for a first player in a captured field of view and determining a spatial association for the first player. The method also includes deriving a global player identification based on the temporal association and the spatial association and generating a trajectory based on the global player identification.

公开(公告)号：US11967086B2

公开(公告)日：2024-04-23

申请号：US17435923

申请日：2019-07-31

Applicant: Intel Corporation

Inventor： Yikai Fang ,  Qiang Li ,  Wenlong Li ,  Chenning Liu ,  Chen Ling ,  Hongzhi Tao ,  Yumeng Wang ,  Hang Zheng

IPC: G06T7/292 ,  A63F13/213 ,  A63F13/42 ,  A63F13/65 ,  G06T7/246 ,  G06T7/70 ,  G06T15/20 ,  G06V10/82 ,  G06V20/40 ,  G06V40/10

CPC classification number: G06T7/246 ,  A63F13/213 ,  A63F13/42 ,  A63F13/65 ,  G06T7/292 ,  G06T7/70 ,  G06T15/20 ,  G06V10/82 ,  G06V20/42 ,  G06V40/10 ,  A63F2300/8082 ,  G06T2207/20084 ,  G06T2207/30221

Abstract: A method for trajectory generation based on player tracking is described herein. The method includes determining a temporal association for a first player in a captured field of view and determining a spatial association for the first player. The method also includes deriving a global player identification based on the temporal association and the spatial association and generating a trajectory based on the global player identification.