视频序列中的运动目标检测与跟踪  

Detection and Tracking of Moving Object in Vedio Sequence

作　　者：李春生[1] 龚晓峰[1] 

机构地区：[1]四川大学电气信息学院,四川成都610065

出　　处：《现代电子技术》2009年第23期149-151,157,共4页Modern Electronics Technique

摘　　要：提出一种视频序列中的运动目标检测跟踪算法。该方法采用直方图统计与多帧平均混合作为动态背景更新法,经过噪音消除、形态学处理、阴影处理后,用区域标记法提取目标。利用目标特征参数建立目标数组,通过当前帧目标数组和前一帧目标数组距离匹配实现运动目标的快速跟踪。该方法与传统方法相比具有更好的学习能力,从而有效地提高了运动目标检测的正确率和快速性。实验结果表明该方法具有良好的鲁棒性和自适应性。An approach is presented to detect and track moving object in video sequence, Considering a method which based on statistics of histogram combining with multi- frame average as dynamic background updating method,the moving object is extracted by using the area earmarking method after some steps including noise eliminating,morphological process, and shadow process. Objectrs array is established according to the characteristic parameters of moving object,and to achieve moving target tracking quickly the distance matching method between current frame and the former frame is introduced. Compared with the traditional method,the proposed method is characterized by better learning ability and scene adaptabiiity and so has effectively improved the detection correct rate and speed. The results of simulation show that the method is robust and adaptive.

关 键 词：背景模型 背景提取 运动目标检测与跟踪 视频序列 

分 类 号：TN919[电子电信—通信与信息系统]