- 专利标题: Human body three-dimensional key point detection method, model training method and related devices
-
申请号: US17352767申请日: 2021-06-21
-
公开(公告)号: US11816915B2公开(公告)日: 2023-11-14
- 发明人: Qingyue Meng
- 申请人: Beijing Baidu Netcom Science and Technology Co., Ltd.
- 申请人地址: CN Beijing
- 专利权人: Beijing Baidu Netcom Science Technology Co., Ltd.
- 当前专利权人: Beijing Baidu Netcom Science Technology Co., Ltd.
- 当前专利权人地址: CN Beijing
- 代理机构: Quinn IP Law
- 优先权: CN 2011238135.3 2020.11.09
- 主分类号: G06V40/00
- IPC分类号: G06V40/00 ; G06V40/10 ; G06T7/70 ; G06T5/50 ; G06F18/214 ; G06V10/764
摘要:
The human body 3D key point detection method includes: acquiring a to-be-detected image, the to-be-detected image including first human body image data; inputting the to-be-detected image into a key point extraction model to acquire N first 3D heatmaps of N human body 3D key points in the first human body image data, each first 3D heatmap representing a Gaussian distribution of one human body 3D key point in first human body image data in a predetermined space, where N is a positive integer; and determining coordinate information about the N human body 3D key points in the first human body image data based on the N first 3D heatmaps.
公开/授权文献
信息查询