基于窗口的 Surf 目标跟踪.pdfVIP

2014年7月 安徽大学学报(自然科学版) July2014 第38卷 第4期 Journal of Anhui University (Natural Science Edition) Vol.38 No.4 doi:10.3969/ j.issn.1000-2162.2014.04.005 基于窗口的Surf 目标跟踪 1 2 倪郁东 ,王 晨 (1.合肥工业大学 数学学院,安徽 合肥 230009;2.合肥工业大学 电气工程与自动化学院,安徽 合肥 230009) 摘 要:为解决Sift在目标跟踪中实时性不高的问题,提出了基于窗口的Surf 目标跟踪方法.相比Sift 目标跟 踪,快速鲁棒尺度不变Surf在速度上有了一定的提高.为进一步提高算法的实时性,只对视频图像中包含目 标的局部窗口提取Surf特征点.利用特征点之间的相对信息,采用仿射变换方法计算跟踪目标窗口的大小, 并获得目标的大致位置信息,最后使用Kalman滤波器对窗口大小和位置信息平滑处理.实验结果表明,该方 法在提升速度的同时,对目标发生尺寸变化及旋转等情况时能准确地跟踪物体. 关键词:Sift;Surf;Kalman滤波器;窗口;目标跟踪 中图分类号:TP391 文献标志码:A 文章编号:1000-2162(2014)04-0027-06 Fast Surf object tracking based on window 1 2 NI Yu-dong ,WANG Chen (1. School of Mathematics,Hefei University of Technology,Hefei 230009,China; 2. School of Electrical Engineering and Automation,Hefei University of Technology,Hefei 230009,China) Abstract:In order to solve the problem that the performance of Sift wasnot high in real-time,fast Surf object tracking based on window was proposed in this paper. Compared with Sift,Surf had a more improvement incomputationalefficiency. Furthermore,inordertoimprovetheefficiency,the Surf features were extracted from local window that only contains the tracking object. Through utilizing the relative information among feature points and the affine transform,the size and position of the tracking window could be calculated. Finally,kalman filter was used to smooth information about the size and location. Experimental results showed that the proposed method could adapt to changes of scale an