Real-time Local Texture Feature Target Tracking Method

摘要：

Precision and Speed are two conflict indexes in target tracking system. Good feature extracting method is key to precision. Local texture feature has better performance when target rotated or illumination changed. Moreover, its compute time is very short In order to accelerate tracking algorithm, a new target tracking method is presented by combines the local texture feature and different value pyramid match methods. Experiment results indicate that the precision of this method is more than the traditional methods and the target displacement can be computed less than 20 ms which can meet the requirements of real time target tracking system.

关键词： LBP target track model matching pyramid mehtod

作者: Hua-jun SONG Yan-jiang WANG

作者单位: College of Information and Control Engineering China University of Petroleum(East China) DongYing, China

会议类型: 国际会议

会议名称: 2011 4th International Congress on Image and Signal Processing(第四届图像与信号处理国际学术会议 CISP 2011)

会议地点: 上海

会议语种:英文

页码: 429-432

在线出版日期: 2011-10-15（万方平台首次上网日期，不代表论文的发表时间）