Login| Sign Up| Help| Contact|

Patent Searching and Data


Title:
KEY POINT DETECTION METHOD AND APPARATUS, ELECTRONIC DEVICE, STORAGE MEDIUM, AND COMPUTER PROGRAM
Document Type and Number:
WIPO Patent Application WO/2021/196718
Kind Code:
A1
Abstract:
A key point detection method and apparatus, an electronic device, a storage medium, and a computer program. The method comprises: determining a target image comprising a target object (S101); carrying out first key point detection on the target image, so as to obtain key position information of the target object, wherein the key position information comprises first key point information on the target object, and position point information of a detection frame corresponding to at least one target part of the target object (S102); on the basis of position point information of a detection frame corresponding to each target part in the at least one target part of the target object, carrying out second key point detection on an image area of each target part in the target image, so as to obtain second key point information corresponding to each target part (S103); and on the basis of the first key point information and the second key point information, determining object key point information of the target object (S104).

Inventors:
JIN SHENG (CN)
LIU WENTAO (CN)
QIAN CHEN (CN)
Application Number:
PCT/CN2020/135394
Publication Date:
October 07, 2021
Filing Date:
December 10, 2020
Export Citation:
Click for automatic bibliography generation   Help
Assignee:
BEIJING SENSETIME TECH DEVELOPMENT CO LTD (CN)
International Classes:
G06K9/46; G06N3/04
Foreign References:
CN111444928A2020-07-24
CN110222685A2019-09-10
CN108229293A2018-06-29
CN108229492A2018-06-29
Other References:
KE SUN; BIN XIAO; DONG LIU; JINGDONG WANG: "Deep High-Resolution Representation Learning for Human Pose Estimation", ARXIV.ORG, 25 February 2019 (2019-02-25), 201 Olin Library Cornell University Ithaca, NY 14853 , XP081032951
Attorney, Agent or Firm:
BEIJING BESTIPR INTELLECTUAL PROPERTY LAW CORPORATION (CN)
Download PDF: