视频运动目标检测与跟踪算法研究及OpenCV实现  

Research of Video Moving Object Detection and Tracking Algorithm and OpenCV Implementation

作　　者：南江丽[1] 王秋光[1] 

机构地区：[1]哈尔滨理工大学电气与电子工程学院,黑龙江哈尔滨150040

出　　处：《哈尔滨理工大学学报》2009年第A01期161-164,共4页Journal of Harbin University of Science and Technology

摘　　要：针对固定场景，给出了一种视频运动目标检测和跟踪算法．利用混合高斯建模的背景差分法，在复杂背景条件下提取出运动目标，并采用颜色直方图模型为特征的均值平移法，对目标进行跟踪．经OpenCV编程测试，算法可以准确地跟踪运动目标．A Vedio moving object detection and tracking algorithm in stationary scene is presented. The researchers adopt the background difference method of mixture gaussian model to draw the moving object under the complex background condition. Then, mean shift algorithm based on color histogram model as the characteristic is applied to track the moving object. Programmed and tested by the OpenCV, the algorithm can realize the tracking of moving object accurately.

关 键 词：混合高斯模型 均值平移算法 OPENCV 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]