Adaptive epsilon LBP for Background Subtraction

CASIA OpenIR > 多模态人工智能系统全国重点实验室 > 先进时空数据分析与学习

	Adaptive epsilon LBP for Background Subtraction
	Wang, LF; Wu, HY; Pan, CH
	2011
会议名称	COMPUTER VISION - ACCV 2010, PT III
会议录名称	Asian Conference on Computer Vision (ACCV)
页码	560-571
会议日期	2011
会议地点	Queenstown, New Zealand
摘要	Background subtraction plays an important role in many computer vision systems, yet in complex scenes it is still a challenging task, especially in case of illumination variations. In this work, we develop an efficient texture-based method to tackle this problem. First, we propose a novel adaptive ε LBP operator, in which the threshold is adaptively calculated by compromising two criterions, i.e. the description stability and the discriminative ability. Then, the naive Bayesian technique is adopted to effectively model the probability distribution of local patterns in the pixel level, which utilizes only one single ε LBP pattern instead of ε LBP histogram of local region. Our approach is evaluated on several video sequences against the traditional methods. Experiments show that our method is suitable for various scenes, especially can robust handle illumination variations.
收录类别	EI
语种	英语
文献类型	会议论文
条目标识符	http://ir.ia.ac.cn/handle/173211/4722
专题	多模态人工智能系统全国重点实验室_先进时空数据分析与学习
推荐引用方式 GB/T 7714	Wang, LF,Wu, HY,Pan, CH. Adaptive epsilon LBP for Background Subtraction[C],2011:560-571.

条目包含的文件		下载所有文件
文件名称/大小	文献类型	版本类型	开放类型	使用许可
Adaptive epsilon LBP（559KB）	会议论文		开放获取	CC BY-NC-SA	浏览下载