DocumentCode :
2508677
Title :
Action Recognition Using Three-Way Cross-Correlations Feature of Local Moton Attributes
Author :
Matsukawa, Tetsu ; Kurita, Takio
Author_Institution :
Univ. of Tsukuba, Tsukuba, Japan
fYear :
2010
fDate :
23-26 Aug. 2010
Firstpage :
1731
Lastpage :
1734
Abstract :
This paper proposes a spatio-temporal feature using three-way cross-correlations of local motion attributes for action recognition. Recently, the cubic higher-order local auto-correlations (CHLAC) feature has been shown high classification performances for action recognition. In previous researches, CHLAC feature was applied to binary motion image sequences that indicates moving or static points. However, each binary motion image lost informations about the type of motion such as timing of change or motion direction. Therefore, we can improve the classification accuracy further by extending CHLAC to multivalued motion image sequences that considered several types of local motion attributes. The proposed method is also viewed as an extension of popular bag-of-features approach. Experimental results using two datasets shows proposed method outperformed CHLAC features and bag-of-features approach.
Keywords :
gesture recognition; image classification; image motion analysis; image sequences; CHLAC feature; action recognition; bag-of-features approach; binary motion image sequences; classification accuracy; classification performances; cubic higher-order local auto-correlations feature; local motion attributes; motion direction; multivalued motion image sequences; spatio-temporal feature; three-way cross-correlations feature; Cameras; Correlation; Humans; Indexes; Pattern recognition; Robustness; Timing; Action recognition; CHLAC;
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.2010.428
Filename :
5597474
Link To Document :
بازگشت