SIA OpenIR  > 机器人学研究室
Background Reconstruction via Low Rank Tensor Factorization
Shen GP(沈贵萍)1,2,3; Han Z(韩志)1,2; Chen XA(陈希爱)1,2,3; Tang YD(唐延东)1,2; Zhang Y(张杨)1,2,3
Department机器人学研究室
Conference Name2018 10th International Conference on Graphics and Image Processing (ICGIP 2018)
Conference DateDecember 12-14, 2018
Conference PlaceChengdu, China
Source Publication2018 10th International Conference on Graphics and Image Processing (ICGIP 2018)
PublisherSPIE
Publication PlaceBellingham, USA
2018
Indexed ByEI
EI Accession number20192106949172
Contribution Rank1
ISSN0277-786X
ISBN978-1-5106-2828-1
Keywordbackground reconstruction low rank Tensor factorization MoG MRF
AbstractThis paper introduces a new method for background reconstruction. Background reconstruction from video sequences captured by a static camera can be regarded as a low rank factorization problem. Background is the low dimensional subspace restored from the higher dimensional visual data, and foreground is treated as sparse noise of unknown distribution. The existing algorithm could not deal with noise of unknown distribution effectively. Due to the limitation of the matrix decomposition which would lost space structure information, we process video data directly as higher order tensor based on low rank tensor factorization (LRTF). We put forward a new model of foreground by using Mixture of Gaussians (MoG) and Markov Random Field (MRF). Extensive experiments show that our method can effectively construct the background.
Language英语
Document Type会议论文
Identifierhttp://ir.sia.cn/handle/173321/23845
Collection机器人学研究室
Corresponding AuthorShen GP(沈贵萍)
Affiliation1.State Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of Sciences, China
2.Institutes for Robotics and Intelligent Manufacturing, Chinese Academy of Sciences, China
3.University of Chinese Academy of Sciences, China
Recommended Citation
GB/T 7714
Shen GP,Han Z,Chen XA,et al. Background Reconstruction via Low Rank Tensor Factorization[C]. Bellingham, USA:SPIE,2018.
Files in This Item: Download All
File Name/Size DocType Version Access License
Background Reconstru(741KB)会议论文 开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Shen GP(沈贵萍)]'s Articles
[Han Z(韩志)]'s Articles
[Chen XA(陈希爱)]'s Articles
Baidu academic
Similar articles in Baidu academic
[Shen GP(沈贵萍)]'s Articles
[Han Z(韩志)]'s Articles
[Chen XA(陈希爱)]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Shen GP(沈贵萍)]'s Articles
[Han Z(韩志)]'s Articles
[Chen XA(陈希爱)]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: Background Reconstruction via Low Rank Tensor Factorization.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

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