基于改进高斯混合建模和短时稳定度的运动目标检测算法  

A Moving Object Detection Algorithm Based on Improved GMM and Short-term Stability Measure

作　　者：张超[1] 吴小培[1] 周建英[1] 戚培庆[1] 王营冠[2] 吕钊[1] 

机构地区：[1]安徽大学计算智能与信号处理教育部重点实验室,合肥230039 [2]中国科学院上海微系统与信息技术研究所,上海200050

出　　处：《电子与信息学报》2012年第10期2402-2408,共7页Journal of Electronics & Information Technology

基　　金：安徽省科技攻关强警专项(1101b0403030);中国科学院上海微系统与信息技术横向研发基金课题资助

摘　　要：传统高斯混合建模方法中前景模型转换为背景模型的风险随着模型权值在一定更新率下的迭代累加而增大,使得传统方法难以有效检测低速运动目标。该文对高斯混合建模中背景匹配失败时生成的前景模型加以利用并引入短时稳定度指标进行综合判断,在深入挖掘前景模型中包含的运动目标信息和像素点级稳定性的基础上实时区分各像素点的状态。多场景下的实验结果表明,该方法对低速目标达到了更高的检出率。In traditional Gaussian Mixture Modeling （GMM） algorithm, the risk that foreground model changes into background model rises with the cumulating of model weight under certain learning rate. That makes the algorithm unable to deal with slow moving object. This paper proposes an algorithm which takes advantage of the foreground models and employs an index of short-term stability measure to make a compound judgment. Each pixel status is decided real-timely considering the information of moving objects contained in foreground models and the pixel-level stability status. The results from different experiments verify that the proposed algorithm achieves a higher detection rate in detecting slow moving objects.

关 键 词：运动目标检测 高斯混合建模 前景模型 短时稳定度 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]