In this paper, we propose to use Mediapipe, which is a Microsoft built-in framework for 3D human pose estimation. The test was evaluated against the MADS (Martial Arts, Dancing, and Sports Dataset) database, in which we focused on sports videos such as: basketball, volleyball, football, rugby, tennis and badminton. The average estimate error is between 100-200mm. The 3D human posture estimation results are a good result in supporting sports analysis.
Nội dung trích xuất từ tài liệu:
3D human pose estimation from sport videos using mediapipe framework
3D human pose estimation from sport videos using mediapipe framework
Số trang: 11
Loại file: pdf
Dung lượng: 0.00 B
Lượt xem: 70
Lượt tải: 0
Thông tin tài liệu:
Tìm kiếm theo từ khóa liên quan:
Tạp chí Khoa học Đại học Tân Trào 3D human pose estimation Mediapipe framework 3D human skeleton Hand action recognition Human-machine interaction Sports analysis Microsoft built-in frameworkTài liệu có liên quan:
-
9 trang 166 0 0
-
Vietnam sea festival in tourism development
8 trang 47 0 0 -
Inflation and axion dark matter in the 3-3-1 model
8 trang 40 0 0 -
A new projection algorithm for solving the split variational inequality problem in hilbert spaces
8 trang 33 0 0 -
9 trang 32 0 0
-
Gender prejudices toward female scientists' position in the family and the workplace
9 trang 32 0 0 -
The predictive validity of standardised test of English proficiency in Vietnam (VSTEP)
8 trang 31 0 0 -
Application of building information model (BIM) in the construction and using in water supply system
8 trang 31 0 0 -
Phân tích hiệu quả kinh tế mô hình trồng cam hữu cơ tại Tuyên Quang
7 trang 29 0 0 -
The effect of perceived risk on intention to use mobile banking in Hanoi
8 trang 27 0 0
