Tensor learningusing N-mode SVD for dynamic background modelling and subtraction

Sheheryar Khan, Guoxia Xu, Hong Yan

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Background modelling and subtraction is an essential component in motion analysis with wide range of applications in computer vision, whereas the task becomes more challenging in context of complex scenarios such as dynamic backgrounds. In this paper, we address the problem of modelling dynamic backgrounds in online tensor leaning framework. We use Tucker decomposition to model thespatio-temporal correlation of video background. To facilitate the online execution of foreground detection, we incrementally update the subspace factor matrices and core tensor by using the N-mode SVD. For the upcoming frame, the estimate of new basis matrix is updated, whereas the contents from last observation are removed. Similarity measure based on pixel values is carried out to produce the foreground mask. Visual analysis on video datasets has revealed that the proposed approach is well suited against dynamically varying backgrounds. Our quantitative results show that the proposed strategy is superior to state-of-the-art methods.

Original languageEnglish
Title of host publicationRPC 2017 - Proceedings of the 2nd Russian-Pacific Conference on Computer Technology and Applications
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages6-10
Number of pages5
ISBN (Electronic)9781538612064
DOIs
Publication statusPublished - 5 Dec 2017
Event2017 IEEE International Conference on Cyber Conflict U.S., CyCon U.S. 2017 - Washington, United States
Duration: 7 Nov 20178 Nov 2017

Publication series

NameRPC 2017 - Proceedings of the 2nd Russian-Pacific Conference on Computer Technology and Applications
Volume2017-December

Conference

Conference2017 IEEE International Conference on Cyber Conflict U.S., CyCon U.S. 2017
Country/TerritoryUnited States
CityWashington
Period7/11/178/11/17

Keywords

  • background subtraction
  • incremental n-mode SVD
  • tensor learning

Fingerprint

Dive into the research topics of 'Tensor learningusing N-mode SVD for dynamic background modelling and subtraction'. Together they form a unique fingerprint.

Cite this