Atomic human action segmentation using a spatio-temporal probabilistic framework

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

研究成果: 書貢獻/報告類型會議貢獻

3 引文 斯高帕斯(Scopus)

摘要

In this paper, a framework for automatic atomic human action segmentation in continuous action sequences is proposed A star figure enclosed by a bounding convex polygon is used to effectively and uniquely represent the extremities of the silhouette of a human body. Thus, human actions are recorded as a sequence of the star figure's parameters, which is then used for action modeling. To model human actions in a compact manner while characterizing their spatiotemporal distributions, star figure parameters are represented by Gaussian mixture models (GMM). Experiments to evaluate the performance of the proposed framework show that it can segment continuous human actions in an efficient and effective manner.
原文英語
主出版物標題Proceedings - 2006 International Conference on Intelligent Information Hiding and Multimedia Signal Processing, IIH-MSP 2006
頁面327-330
頁數4
DOIs
出版狀態已發佈 - 2006
事件2006 International Conference on Intelligent Information Hiding and Multimedia Signal Processing, IIH-MSP 2006 - Pasadena, CA, 美国
持續時間: 12月 18 200612月 20 2006

出版系列

名字Proceedings - 2006 International Conference on Intelligent Information Hiding and Multimedia Signal Processing, IIH-MSP 2006

會議

會議2006 International Conference on Intelligent Information Hiding and Multimedia Signal Processing, IIH-MSP 2006
國家/地區美国
城市Pasadena, CA
期間12/18/0612/20/06

ASJC Scopus subject areas

  • 一般電腦科學

指紋

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

引用此