DocumentCode :
2515565
Title :
Encoding Actions via Quantized Vocabulary of Averaged Silhouettes
Author :
Wang, Liang ; Leckie, Christopher
Author_Institution :
Dept. of Comput. Sci., Univ. of Bath, Bath, UK
fYear :
2010
fDate :
23-26 Aug. 2010
Firstpage :
3657
Lastpage :
3660
Abstract :
Human action recognition from video clips has received increasing attention in recent years. This paper proposes a simple yet effective method for the problem of action recognition. The method aims to encode human actions using the quantized vocabulary of averaged silhouettes that are derived from space-time windowed shapes and implicitly capture local temporal motion as well as global body shape. Experimental results on the publicly available Weizmann dataset have demonstrated that, despite its simplicity, our method is effective for recognizing actions, and is comparable to other state-of-the-art methods.
Keywords :
encoding; image recognition; quantisation (signal); Weizmann dataset; action recognition; averaged silhouettes; human action recognition; local temporal motion; quantized vocabulary; space-time windowed shapes; video clips; Feature extraction; Hidden Markov models; Humans; Shape; Support vector machines; Visualization; Vocabulary; clustering; human action recognition; space-time silhouettes;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Pattern Recognition (ICPR), 2010 20th International Conference on
Conference_Location :
Istanbul
ISSN :
1051-4651
Print_ISBN :
978-1-4244-7542-1
Type :
conf
DOI :
10.1109/ICPR.2010.892
Filename :
5597840
Link To Document :
بازگشت