Entropy-based Action Features Selection Using Histogram Intersection Kernel

摘要：

Current approaches of local spatio-temporal interest point detections provide compact but descriptive representations for human action recognition. However, unavoidable noisy points interfering with video representation lead to bringing the accuracy of recognition down. This paper proposes an efficient approach to select human action features in videos. We combine entropy with histogram intersection kernel incorporating method of feature distance measurement in similarity to compute histogram significance. The accuracy of our method tested on the KTH dataset using 3D-Harris detector and 3D-HoG descriptor is 83.52％. Experimental results demonstrate that our method with distance of Histogram Intersection to build visual code words has a positive impact upon selecting features which are beneficial to classification.

关键词： entropy Histogram Intersection action recognition

作者: Shu Liu Shao-Zi Li Xian-Ming Liu Hong-Bo Zhang

作者单位: Fujian Key lab of brain-like intelligent system, Xiamen, Fujian, China, 361005 Dept.of Cognitive Science, Xiamen University, Fujian, China, 361005 Fujian Key lab of brain-like int

会议类型: 国际会议

会议名称: 2010 2nd International Conference on Signal Processing System(2010年信号处理系统国际会议 ICSPS 2010)

会议地点: 大连

会议语种:英文

页码: 2295-2298

在线出版日期: 2010-07-05（万方平台首次上网日期，不代表论文的发表时间）