一种基于改进均值漂移的实时目标检测与跟踪算法

来源期刊:中南大学学报(自然科学版)2011年第z1期

论文作者:雷颖惠 张娟 杨文佳

文章页码:823 - 828

关键词:卡尔曼滤波;均值漂移;目标检测;目标跟踪

Key words:Kalman filter; mean shift; moving foreground segmentation; moving object tracking

摘    要:针对随动监控系统下的运动前景目标,提出一种改进的实时目标检测与跟踪方法。首先,在运动目标初次进入视频场景时,通过基于自适应混合高斯模型的方法提取运动目标。然后,利用融合了卡尔曼滤波的均值漂移算法对运动目标进行预测跟踪,使其能处于随动系统的视野中心。提出的算法既保证了检测跟踪的实时性,又增大了对运动目标进行跟踪的视野范围。实验结果表明:该算法能够实时自动地对运动目标进行检测与随动跟踪。

Abstract: An improved real-time target detection and tracking method was proposed based on moving foreground object in the servo monitoring system. This method extracts moving object based on adaptive mixture of Gaussian when the object comes into the video scene, then tracks the moving object using improved MeanShift algorithm, and makes it in the center of the scene. The algorithm not only ensures the real-timing of the detection and tracking, but also enlarges the sight of the camera when the object is tracked. The experiment results show that this method can automatically detect moving object and do servo tracking.

有色金属在线官网  |   会议  |   在线投稿  |   购买纸书  |   科技图书馆

中南大学出版社 技术支持 版权声明   电话:0731-88830515 88830516   传真:0731-88710482   Email:administrator@cnnmol.com

互联网出版许可证:(署)网出证(京)字第342号   京ICP备17050991号-6      京公网安备11010802042557号