Adaptive eLBP 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 eLBP for Background Subtraction
	LingFeng Wang; Huai-Yu Wu; Chunhong Pan
	2010
会议名称	The Asian Conference on Computer Vision (ACCV 2010)
会议录名称	The Asian Conference on Computer Vision (ACCV 2010)
会议日期	2010
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 εLBP 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 εLBP pattern instead of εLBP 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.
关键词	Adaptive Elbp For Background Subtraction
文献类型	会议论文
条目标识符	http://ir.ia.ac.cn/handle/173211/12144
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
通讯作者	Huai-Yu Wu
作者单位	NLPR, CASIA
推荐引用方式 GB/T 7714	LingFeng Wang,Huai-Yu Wu,Chunhong Pan. Adaptive eLBP for Background Subtraction[C],2010.