A robust background subtraction approach with a moving camera

Xiaochun Zou, Xinbo Zhao, Zheru Chi

Research output: Chapter in book / Conference proceedingConference article published in proceeding or bookAcademic researchpeer-review

7 Citations (Scopus)

Abstract

In this paper, an algorithm for extracting moving objects from a moving background scene that contains complex camera motion is proposed. The robust and efficiently background subtraction algorithm that is able to cope with local scene changes, such as audiences and trees, as well as globe scene changes caused by camera motion. The algorithm is based on a proposed background subtraction method and comprises three steps: the feature-based camera motion estimation, panorama reconstruction and background subtraction. The background subtraction in our method, which introduces risk maps to account for the problem that the background image may not be perfectly aligned to the input images, greatly improves the foreground separation even on the object boundary. We have applied this method to standard image sequences. Experimental results show the proposed method can be successfully provided with the background subtraction capability.
Original languageEnglish
Title of host publicationProceedings - 2012 7th International Conference on Computing and Convergence Technology (ICCIT, ICEI and ICACT), ICCCT 2012
Pages1026-1029
Number of pages4
Publication statusPublished - 1 Dec 2012
Event2012 7th International Conference on Computing and Convergence Technology (ICCIT, ICEI and ICACT), ICCCT 2012 - Seoul, Korea, Republic of
Duration: 3 Dec 20125 Dec 2012

Conference

Conference2012 7th International Conference on Computing and Convergence Technology (ICCIT, ICEI and ICACT), ICCCT 2012
Country/TerritoryKorea, Republic of
CitySeoul
Period3/12/125/12/12

Keywords

  • Background Subtraction
  • Motion Estimation
  • Panorama Reconstruction

ASJC Scopus subject areas

  • Computer Science Applications
  • Software

Fingerprint

Dive into the research topics of 'A robust background subtraction approach with a moving camera'. Together they form a unique fingerprint.

Cite this