一种基于多重判别的运动目标检测算法  

A Moving Object Detection Algorithm Based on Multiple Judgments

作　　者：李孟歆[1] 范静静[1] 张颖[1] 许伟靖[1] 侯丁丁[1] 

机构地区：[1]沈阳建筑大学信息与控制工程学院,辽宁沈阳110168

出　　处：《沈阳建筑大学学报（自然科学版）》2013年第4期750-756,共7页Journal of Shenyang Jianzhu University：Natural Science

基　　金：国家自然科学基金项目(60874103)

摘　　要：目的为改善传统的背景差分法对光照的敏感性,并提高其抗干扰性能,提出一种基于多重判别的运动目标检测算法.方法通过matlab软件进行仿真,利用局部二值算法,将纹理信息和颜色信息融入到背景建模中,并与帧间差分法相结合,设定了两个阈值,进行运动目标的多重判断,利用像素灰度值的变化和变化的像素数量作为是否为感兴趣运动目标的判别依据.结果多重判别的运动目标检测算法将人和车辆从背景中清晰的分离出来,并能保证运动目标的完整性.结论算法能够准确的检测出运动目标,并能抵御场景中缓慢而微小的运动带来的干扰,具有较好的鲁棒性.The traditional background subtraction method is more sensitive to light and shows poor anti-interference performance.A moving object detection algorithm based on multiple judgments is proposed.The Local Binary Pattern（LBP）algorithm is considered to put texture information into the background model,combining color and texture information and an improved background subtraction method proposed.In addition,a new method is proposed combining the inter-frame difference method with improved background subtraction method in this paper.The method made use of dual-threshed to detect moving targets and make multiple judgments.It not only used the change of pixel gray value to detect moving targets,but also took advantage of the number of changed pixels to detect moving targets interested in.The algorithm uses people and vehicles as moving targets to be detected through mat lab.The experiment showed that the algorithm was able to detect the moving target accurately and can resist interferences which were brought about by the slow sand slight movements in the scene with better robustness.

关 键 词：运动目标检测 背景差分 局部二值算法 帧间差分 多重判断 

分 类 号：TN216[电子电信—物理电子学]