基于角点采样的多目标跟踪方法  

Tracking Multiple Objects Method Based on Harris Corner Sampling

作　　者：刘闯[1] 龚声蓉[1] 崔志明[1] 刘纯平[1] 夏侯玉娇[1] 

机构地区：[1]苏州大学计算机科学与技术学院,苏州215006

出　　处：《中国图象图形学报》2008年第10期1873-1877,共5页Journal of Image and Graphics

基　　金：国家自然科学基金项目(60673092);教育部科研重点项目(207040);江苏省高校自然科学基金项目(07KJD520186)

摘　　要：为了跟踪互遮挡的多个目标,提出了一种基于角点采样的多目标跟踪方法。该方法以遮挡发生前的各目标区域中的Harris角点信息为样本,在遮挡发生情况下,采取K近邻分类器对目标区域中提取的角点信息进行分类,以有效区分遮挡在一起的多个目标。在角点特征提取过程中,还提出了双阈值Harris角点检测算法,用于自适应、准确地提取运动区域中角点信息。实验结果表明,该方法能有效区分遮挡在一起,且没有分裂之前的多个目标。To track multiple objects which were occluded each other, a multi-target tracking method based on the sampled corners was proposed, which extracted Harris corner information as the training sample before occluding and used K nearest neighborhood （KNN） classifier to classify the corners in the occluding region. And this method can effectively distinct multiple targets through occlusion. In the process of extracting corners, the dual-threshold Harris corner detection algorit-hm was proposed. It can adaptively and accurately extract corners. The experimental results show that the proposed method can effectively track multiple objects which were occluded and didn＇ t split up.

关 键 词：多目标跟踪 角点检测 角点采样 K近邻分类器 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]