单目智能视觉监视应用中小运动目标的检测

Detecting Small Moving Objects for a Monocular Automatic Visual Surveillance System

提出了以Cauchy分布作为图像像素比值的统计分布模型 ,并融合图像局部线性相关技术实现背景建模。该方法同时利用了像素点的统计特性和邻近像素点所蕴涵的丰富空间区域信息。实验表明 ,本文提出的算法可以抗背景中全局或局部光照的渐变和突变 ,有效地抑制背景中活动物体和阴影的杂波干扰。

An algorithm based on a Cauchy distribution statistical model of a scene background is presented to detect low resolution moving objects for monocular automatic visual surveillance system. A robust background subtracting based on moving object detecting approach is acquired by hypothesis test. Experimental results demonstrate the proposed algorithms can tolerate the whole or local sudden or slow changes in illumination, filter clutter noises caused by small motions in background scene, and adapt to rain or haze. The detecting results of the proposed algorithm are better than those of the Gaussian statistical model or the shading model.