首页 | 本学科首页   官方微博 | 高级检索  
     

视觉监视中基于柯西分布的统计变化检测
引用本文:明英,蒋晶珏. 视觉监视中基于柯西分布的统计变化检测[J]. 中国图象图形学报, 2008, 13(2): 328-334
作者姓名:明英  蒋晶珏
作者单位:清华大学电子工程系,武汉大学计算机学院 北京100084,武警武汉指挥学院,武汉430064,武汉430079
基金项目:国家“863”高技术研究发展计划导向类项目(SQ2006AA12Z108506)
摘    要:为了更好地进行视觉监视,该文给出了一种新的基于柯西分布的光照不变的统计变化检测算法。该算法首先将两帧图像间的灰度比值作为背景建模和剔除的特征,并且在假定背景图像中,当每个像素点观测的时序灰度变化由白噪声引起时,两帧背景图像中对应像素间的灰度比值的分布符合柯西分布;然后基于该变化检测方法,将YCbCr颜色空间的亮度、色调和饱和度用来识别和消除视频序列图像中的阴影。实验结果表明,该新算法不仅可以承受整体或局部的、缓慢或突然的光线变化,并且可以滤除由场景背景中小的扰动而导致的噪声。

关 键 词:变化检测  运动目标检测  背景建模  阴影  柯西分布  监视
文章编号:1006-8961(2008)02-0328-07
收稿时间:2007-04-21
修稿时间:2007-04-21

Cauchy Distribution Based on Statistical Change Detection for Visual Surveillance
MING Ying,JIANG Jing-jue and MING Ying,JIANG Jing-jue. Cauchy Distribution Based on Statistical Change Detection for Visual Surveillance[J]. Journal of Image and Graphics, 2008, 13(2): 328-334
Authors:MING Ying  JIANG Jing-jue  MING Ying  JIANG Jing-jue
Affiliation:(Department of Electronic Engineering, Tsinghua University, Beijing 100084) (School of Computer Science, Wuhan University, Wuhan 430079) (Education department, Wuhan Command School of Armed Police Force, Wuhan 430064)
Abstract:A novel illumination-invariant change detection algorithm based on Cauchy distribution is proposed.The intensity ratios between two images are used as the feature to model and subtract background.The distribution of the intensity ratios between corresponding pixels of two background images follows Cauchy distribution,assuming that some observed temporal intensity variation of each pixel in background images are caused by white noise.The intensity,hue and saturation in the YCbCr color space are employed to recognize and eliminate shadows in video sequences.Finally,experimental results demonstrate that the proposed algorithm can tolerate the whole or local quick or slow changes in illuminations,and can filter noise caused by small motion in scene background.
Keywords:change detection  moving object detection  background modeling  shadows  Cauchy distribution  surveillance
本文献已被 CNKI 维普 万方数据 等数据库收录!
点击此处可从《中国图象图形学报》浏览原始摘要信息
点击此处可从《中国图象图形学报》下载免费的PDF全文
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号