基于码书和纹理特征的运动目标检测

被引：4

作者：

李波 ^{[1
,2
]}

袁保宗 ^{[1
,2
]}

机构：

[1] 北京交通大学信息科学研究所

[2] 现代信息科学与网络技术北京市重点实验室

来源：

信号处理 | 2011年 / 27卷 / 06期

关键词：

运动目标检测; 码书; 高斯局部二值模式; 背景模型;

D O I：

暂无

中图分类号：

TP391.41 [];

学科分类号：

080203 ;

摘要：

复杂环境下如何进行鲁棒的运动目标检测是计算机视觉领域热门研究课题。本文提出了一种新的码书和高斯局部二值模式(GLBP)的纹理描述的运动物体检测方法,在线学习构建码书纹理背景模型。首先用码书以类似聚类的方式构建每个像素的码书模型,根据码字的颜色和亮度相似性,将背景像素分布用聚类码字的形式表示出来,同时在模型初始化和运动检测阶段不断更新码字以反映背景变化。然后用单高斯模型来学习背景像素变化的概率,生成GLBP纹理算子,同时在线更新GLBP反映图像空间纹理信息变化。最后融合三个特征将当前帧分割为前景背景两部分。通过实验视频表明本方法在实际视频中取得了较好的鲁棒的效果。

引用

页码：912 / 918

页数：7

共 10 条

[1] Multiresolution gray-scale and rotation invariant texture classification with local binary patterns. Ojala T,Pietikainen M,Maenpaa T. IEEE Transactions on Pattern Analysis and Machine Intelligence . 2002
[2] Background and foreground modeling using nonparametric kernel density estimation for visual surveillance. Elgammal A,Duraiswami R,Harwood D,et al. Proceedings of Tricomm . 2002
[3] Pfinder: real-time tracking of human body. Wren CR,Azarbayejani A,Darrell T,Pentland AR. IEEE Transactions on Pattern Analysis and Machine Intelligence . 1997
[4] Understanding background mixture models for foreground segmentation. P W Power,J A Schoonees. Proceedings Image and Vision Computing . 2002
[5] A comparative study of texture measures with classification based on featured distributions[J] . &nbspPattern Recognition . 1996 (1)
[6] Segmentation of Moving Foreground Ob- jects Using Codebook and Local Binary Patterns. Li,B.et al. Image and Signal Processing,2008.CISP’’08.Congress on . 2008
[7] Background modeling and subtraction by codebook construction. Kyungnam,K.et al. Image Processing,2004. ICIP’’04.2004 International Conference on . 2004
[8] Dynamic texture recognition using local binary patterns with an application to facial expressions. ZHAO G,PIETIKAINEN M. IEEE Transactions on Pattern Analysis and Machine Intelligence . 2007
[9] Face description with local binarypatterns:Application to face recognition. Ahonen T,,Pietikainen H A. IEEE Transactions on Pattern Analysis and Machine Intelligence . 2006
[10] A comparative study of texture measures with classification based on feature distributions. Ojala T,Pietikainen M,Harwood D. Pattern Recognition . 1996

← 1 →