视频序列中运动目标的检测与跟踪方法  

Detection and Tracking Algorithm for Moving Object in Video Sequence

作　　者：吕利娟[1] 陈建春[1] 

机构地区：[1]西安电子科技大学电子工程学院,陕西西安710071

出　　处：《电子科技》2010年第9期92-95,共4页Electronic Science and Technology

摘　　要：提出了一种视频序列中运动目标的检测与跟踪算法,该算法采用基于码本背景建模的减背景法与差分法相结合的算法,实现对运动目标的快速精确的检测与提取,也能够在存在前景运动的过程中提取背景,使用卡尔曼滤波对运动目标在下一帧中最可能出现的位置进行估计,在此基础上利用Camshift跟踪算法进行较小范围的搜索和目标匹配,减少了运算量、节约了搜索和匹配的时间、提高了跟踪的速度。实验证明该方法具有一定的实用性。This paper presents a detection and tracking algorithm for moving object in video sequence.A combination of the difference and the background subtraction based on codebooks background modeling,the algorithm can have accurate object detection and extraction of the moving object.It can also extract background with the existence of moving foregrounds.A kalman filter is used to predict the moving object＇s position at the next moment,so that by Camshift tracking algorithm,search and object matching can be made over a smaller range,thus reducing the amount of calculation,saving the searching and matching time and improving the tracking efficiency.Experiment shows that this algorithm is of practical value.

关 键 词：码本 背景建模 卡尔曼滤波 CAMSHIFT 

分 类 号：TP301.6[自动化与计算机技术—计算机系统结构]