Continuous human action segmentation and recognition using a spatio-temporal probabilistic framework

Duan Yu Chen, Hong Yuan Mark Liao, Sheng Wen Shih

研究成果: 書貢獻/報告類型會議貢獻

11 引文 斯高帕斯(Scopus)

摘要

In this paper, a framework of automatic human action segmentation and recognition in continuous action sequences is proposed. A star-like figure is proposed to effectively represent the extremities in the silhouette of human body. The human action, thus, is recorded as a sequence of the star-like figure parameters, which is used for action modeling. To model human actions in a compact manner while characterizing their spatio-temporal distributions, star-like figure parameters are represented by Gaussian mixture models (GMM). In addition, to address the intrinsic nature of temporal variations in a continuous action sequence, we transform the time sequence of star-like figure parameters into frequency domain by discrete cosine transform (DCT) and use only the first few coefficients to represent different temporal patterns with significant discriminating power. The performance shows that the proposed framework can recognize continuous human actions in an efficient way.
原文英語
主出版物標題ISM 2006 - 8th IEEE International Symposium on Multimedia
頁面275-282
頁數8
DOIs
出版狀態已發佈 - 2006
事件ISM 2006 - 8th IEEE International Symposium on Multimedia - San Diego, CA, 美国
持續時間: 12月 11 200612月 13 2006

出版系列

名字ISM 2006 - 8th IEEE International Symposium on Multimedia

會議

會議ISM 2006 - 8th IEEE International Symposium on Multimedia
國家/地區美国
城市San Diego, CA
期間12/11/0612/13/06

ASJC Scopus subject areas

  • 電腦網路與通信

指紋

深入研究「Continuous human action segmentation and recognition using a spatio-temporal probabilistic framework」主題。共同形成了獨特的指紋。

引用此