������Ƶ���е����˶�Ŀ����ٷ����о�

本文研究了基于视频序列的行人多目标跟踪方法。首先利用视频图像处理技术实现背景提取、背景更新、移动目标检测。然后利用移动行人在相邻两帧图像上位置和面积的变化特点，建立匹配矩阵，完成移动目标的匹配，实现多目标跟踪；最后利用实测的视频数据检验算法，实验结果表明，该方法能清楚地绘出行人的移动轨迹，分析了跟踪轨迹中噪声产生的原因。

A Study on Moving Pedestrian Tracking Based on Video Sequences

The study on tracking of moving pedestrians based on vision sequence is presented in the paper.The video sequences are processed by the background extraction and adaptation,moving objects detection,shadow detection,eroding and dilating image in order to create the moving pedestrian contour.The change of the moving pedestrian contour location and area is taken into account by the method presented here.The method first computes the centre coordinates and radius of the circle through the pedestrian contour.Secondly,the matching matrix is established by the change of the location and the radius between the different circles at two successive frames and the matching moving objects have been found.The method is tested by using the video sequences of actual measurement and the experiment results are analyzed.Under the experiment condition,the contrails of the moving pedestrians are clearly drawn with a little noise at the different image sampling interval.Finally,the application condition of the method is described.