A reduced LTP coding on spatial interest points for Human Action Recognition

摘要：

　　We present a novel action recognition method which is based on combining detecting 2D informative feature points and coding their local changes in motion directions by Local Trinary Patterns.The resulting method is extremely efficient,and thus is suitable for real-time uses of simultaneous recovery of human action of several lengths and starting points.Tested on some publicity available datasets in the literature known to us,our method can make good performance both on accuracy and efficiency for recognition.

关键词： reduced LTP interest points action recognition

作者: Chunkeng Dong Hao Song

作者单位: School of Communication & Information Engineering UESTC Chengdu,China School of Electronic Engineering UESTC Chengdu,China

会议类型: 国际会议

会议名称: 2013 2nd International Conference on Computer Science and Electronics Engineering(ICCSEE2013)(2013年第二届计算机科学与电子工程国际会议)

会议地点: 杭州

会议语种:英文

页码: 1077-1080

在线出版日期: 2013-03-22（万方平台首次上网日期，不代表论文的发表时间）