Human Action Recognition Using Spatio-Temoporal Descriptor

被引:0
作者
Li, Chuanzhen [1 ]
Su, Bailiang [1 ]
Liu, Yin [1 ]
Wang, Hui [2 ]
Wang, Jingling [2 ]
机构
[1] Commun Univ China, Sch Informat Engn, Beijing, Peoples R China
[2] Commun Univ China, KLMAV Lab, Beijing, Peoples R China
来源
2013 6TH INTERNATIONAL CONGRESS ON IMAGE AND SIGNAL PROCESSING (CISP), VOLS 1-3 | 2013年
基金
中国国家自然科学基金;
关键词
human action recognition; 3D SURF; bag-of-words;
D O I
暂无
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
A novel and efficient human action recognition method utilizing spatio-temporal interest point detector and 3D speed up robust features (3D SURF) descriptor is proposed. The spatio-temporal interest points are detected using two separate linear filters. Then 3D SURF descriptor is presented and demonstrated in detail to represent the local region around interest point. The experimental results on KTH and Weizmann dataset prove that the proposed method is superior to similar methods. Especially, compared with the popular 3DSIFT, 3D SURF is advantage in recognition rate and lower computation cost as well.
引用
收藏
页码:107 / 111
页数:5
相关论文
共 21 条
[1]   Human action recognition using shape and CLG-motion flow from multi-view image sequences [J].
Ahmad, Mohiuddin ;
Lee, Seong-Whan .
PATTERN RECOGNITION, 2008, 41 (07) :2237-2252
[2]  
[Anonymous], 2007, 2007 IEEE C COMP VIS
[3]  
[Anonymous], EUR C COMP VIS ECCV
[4]  
[Anonymous], 2008, BMVC 2008 19 BRIT MA
[5]  
[Anonymous], 2011, ACM T INTEL SYST TEC, DOI DOI 10.1145/1961189.1961199
[6]  
[Anonymous], P IEEE C COMP VIS PA
[7]  
Dollar P., 2005, Proceedings. 2nd Joint IEEE International Workshop on Visual Surveillance and Performance Evaluation of Tracking and Surveillance (VS-PETS) (IEEE Cat. No. 05EX1178), P65
[8]  
Jhuang H., 2007, IEEE 11 INT C COMPUT, P1
[9]   Supervised Learning and Codebook Optimization for Bag-of-Words Models [J].
Jiu, Mingyuan ;
Wolf, Christian ;
Garcia, Christophe ;
Baskurt, Atilla .
COGNITIVE COMPUTATION, 2012, 4 (04) :409-419
[10]  
Knopp J, 2010, LECT NOTES COMPUT SC, V6316, P589, DOI 10.1007/978-3-642-15567-3_43