Human Action Recognition Using Dynamic Time Warping and Voting Algorithm (1)

Pham, Chinh Huu
Le, Quoc Khanh
Le, Thanh Ha
This paper presents a human action recognition method using dynamic time warping and voting algorithmson 3D human skeletal models. In this method human actions, which are the combinations of multiple body part movements, are described by feature matrices concerning both spatial and temporal domains. The feature matrices are created based on the spatial selection of relative angles between body parts in time series. Then, action recognition is done by applying a classifier which is the combination of dynamic time warping (DTW) and a voting algorithm to the feature matrices. Experimental results show that the performance of our action recognition method obtains high recognition accuracy at reliable computation speed and can be applied in real time human action recognition systems.
Chi tiết xin mời tham khảo tại http://repository.vnu.edu.vn/handle/VNU_123/56668
Title:

Human Action Recognition Using Dynamic Time Warping and Voting Algorithm (1)
Authors: Pham, Chinh Huu
Le, Quoc Khanh
Le, Thanh Ha
Keywords: Human action recognition;feature extraction;Dynamic time warping.
Issue Date: 2014
Publisher: ĐHQGHN
Series/Report no.: Vol. 30, No. 3 (2014);
Description:

p. 22-30
URI: http://repository.vnu.edu.vn/handle/VNU_123/56668
ISSN: 0866-8612
Appears in Collections:Computer Science and Communication Engineering

Nhận xét

Bài đăng phổ biến từ blog này

Dự báo nghiệp vụ ngư trường khai thác cá ngừ đại dương trên vùng biển Việt Nam năm 2015-2016

Vinamilk’s Supply Chain and the Small Farmers’ Involvement

Liên kết phát triển sản phẩm du lịch Thái Nguyên với một số tỉnh phía bắc Việt Nam: Lạng Sơn, Cao Bằng, Yên Bái