A Particle Filter Tracking Algorithm Based On SIFT Feature Matching

摘要：

This paper presents a particle filter tracking algorithm based on SIFT feature matching. After target prediction by particle filtering, SIFT features are calculated in the target neighborhood, so some unnecessary calculations are properly omitted, therefore the computational time is reduced greatly and the tracking speed is increased remarkably. Moreover, the features are calculated in the neighborhood of target, so its tracking robustness is increased correspondingly. Experimental results show that the proposed tracking algorithm can better adapt to target tracking under various conditions, with good performances of real-time and robustness.

关键词： SIFT feature matching Particle filtering Target tracking Target neighborhood

作者: Wei Ying Li Juanjuan Wu Di

作者单位: College of Information Science and Engineering, Northeastern University, Shenyang 110004 Key Laborat College of Information Science and Engineering, Northeastern University, Shenyang 110004

会议类型: 国际会议

会议名称: The 24th Chinese Control and Decision Conference (第24届中国控制与决策学术年会 2012 CCDC)

会议地点: 太原

会议语种:英文

页码: 1462-1466

在线出版日期: 2012-05-23（万方平台首次上网日期，不代表论文的发表时间）