基于Kalman滤波理论的运动目标检测新方法  

New method for detecting of moving targets based on Kalman filter theory

作　　者：任臣[1] 张覃平[1] 

机构地区：[1]中国科学院光电技术研究所

出　　处：《光电工程》2007年第4期7-11,共5页Opto-Electronic Engineering

基　　金：国家863高技术项目

摘　　要：该文研究了基于Kalman滤波理论的渐消记忆最小二乘法在图像背景重建中的应用,并将它应用在复杂背景的图像序列中,实现对运动目标的自动检测。首先用渐消记忆最小二乘法对复杂背景进行预测和更新,然后把当前帧与预测的背景模板做差分运算,最后采用自适应阈值分割技术实现对目标的自动分割。文中通过对序列图像的仿真,讨论了最小二乘法的存在问题,改进及适用情况,干扰的消除。试验结果表明,该方法具有很强的实用性。The fading memory recursive least-squares based on Kalman filter is applied to rebuild image background. This method is used for detecting moving targets in the image sequence of clutter background. First, the rebuilt algorithm is adopted to predict and update the image background. And then a difference image can be obtained by subtracting the current frame from the predicted background. At last, the moving targets are automatically segmented by selecting an adaptive threshold. The problems which exist in the fading memory recursive least-squares, the improvement mad the elimination of disturbance are discussed by experiment. Experimental results are given to demonstrate the effectiveness and practicality of the method.

关 键 词：KALMAN滤波 背景预测 自适应闽值选择 运动目标检测 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]