一种多级运动目标检测算法  

An Algorithm for Hierarchical Moving Object Detection

作　　者：曾峦[1] 宋胜利 

机构地区：[1]装备指挥技术学院 [2]63891部队

出　　处：《计算机测量与控制》2010年第6期1231-1233,共3页Computer Measurement &Control

基　　金：总装备部试验技术研究项目(2007SY4112002)

摘　　要：为了提高Javed等提出的运动目标三级检测算法的稳定性,文中对其处理方法做出改进;在像素级处理阶段,采用每一个像素点及其邻域组成的集合作为特征矢量来描述图像,对YUV格式的彩色图像的不同颜色分量分别建立混合高斯模型,得到背景模型后,计算出Sobel边缘检测得到的边缘点的统计分布;在区域级处理阶段,将彩色图像分割与背景建模结合起来,得到具有精确边缘的运动目标,并利用边缘信息消除干扰目标;实验结果表明,即使在前景纹理、颜色比较一致且与背景对比不是很明显的情况下,改进后的方法也能完整地检测出运动目标。To enhance the stability of hierarchical moving object detection algorithm which was presented by Javed et al, this paper improves the processing method. At the processing phase of pixel level, it used a pixel and its neighbors as an image vector to represent image, and construct mixture Gaussians models of different chrominance component of the YUV format color image. Based on the color background model, the statistical distribution of edge detection by Sobel operator was computed. In the processing phase of region level, color segmentation and background model were combined to extract moving objects with pixel-wide precision edge. The area of interferential object was eliminated by using information of the edge of moving objects. Simulation results showed that the improved algorithm can detect intact moving objects even when the foregrounds＇ texture and color are homogeneous and foreground has low contrast with background.

关 键 词：运动目标检测 背景建模 混合高斯模型 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]