Object Tracking and Primitive Event Detection by Spatio-Temporal Tracklet Association

摘要：

Accurate object tracking is a challenging problem in visual surveillance due to noise segmentation, partial and full object occlusions. In this paper, we present a method for object tracking and primitive event detection by associating tracklet caused by these problems. The aim is to keep track identity across tracking gaps and detect objects motion changes (identify primitive event) that cause tracklet gaps. We first detect moving objects and generate tracklet, then grow these tracklets by finding the best spatial and temporal association of observations to track object across tracklet gaps and indentify the video event they involved. We successfully track multiple moving vehicles and persons under occlusion, noisy detections and splitmerge situations and can identify the event that cause tracking gaps.

作者: Wang Jiangfeng Zhang Maojun Anthony G Cohn

作者单位: School of Information Systems and Management National University of Defence Technology, Changsha, Ch School of Computing University of Leeds, Leeds, UK

会议类型: 国际会议

会议名称: The Fifth International Conference on Image and Graphics(第五届国际图像图形学学术会议 ICIG 2009)

会议地点: 西安

会议语种:英文

页码: 457-462

在线出版日期: 2009-09-20（万方平台首次上网日期，不代表论文的发表时间）