CASIA OpenIR  > 模式识别国家重点实验室  > 先进数据分析与学习
Adaptive epsilon LBP for Background Subtraction
Wang, LF; Wu, HY; Pan, CH
Conference NameCOMPUTER VISION - ACCV 2010, PT III
Source PublicationAsian Conference on Computer Vision (ACCV)
Conference Date2011
Conference PlaceQueenstown, New Zealand
AbstractBackground 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.
Indexed ByEI
Document Type会议论文
Recommended Citation
GB/T 7714
Wang, LF,Wu, HY,Pan, CH. Adaptive epsilon LBP for Background Subtraction[C],2011:560-571.
Files in This Item: Download All
File Name/Size DocType Version Access License
Adaptive epsilon LBP(559KB)会议论文 开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Wang, LF]'s Articles
[Wu, HY]'s Articles
[Pan, CH]'s Articles
Baidu academic
Similar articles in Baidu academic
[Wang, LF]'s Articles
[Wu, HY]'s Articles
[Pan, CH]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Wang, LF]'s Articles
[Wu, HY]'s Articles
[Pan, CH]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: Adaptive epsilon LBP for Background Subtraction.pdf
Format: Adobe PDF
All comments (0)
No comment.

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.