公开(公告)号：US20230120054A1

公开(公告)日：2023-04-20

申请号：US17884968

申请日：2022-08-10

Applicant: BEIJING BAIDU NETCOM SCIENCE TECHNOLOGY CO., LTD.

Inventor： Qiansheng YANG

IPC: G06V10/44 ,  G06T7/73 ,  G06T7/50 ,  G06V10/80 ,  G06V40/10

Abstract: There is provided a key point detection method, a model training method, an electronic device and a storage medium, which relates to the field of artificial intelligence, and particularly to computer vision technologies and deep learning technologies, and may be particularly used for scenarios, such as behavior recognition, human-body special effect generation, entertainment game interaction, or the like. The key point detection method includes: extracting features of an image to obtain image features of the image; acquiring graph information of key points of a target in the image based on the image features, the graph information including a location relationship graph of the key points and location information of a central point in the key points; and acquiring location information of non-central points in the key points based on the location relationship graph of the key points and the location information of the central point.