Foreground object detection and tracking for visual surveillance system: A hybrid approach

Seon Ho Oh, Sajid Javed, Soon Ki Jung

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

7 Scopus citations

Abstract

Foreground detection is one of the fundamental preprocessing steps in many image processing and computer vision applications. In spite of significant efforts, however, slowly moving foregrounds or temporarily stationary foregrounds remains challenging problem. To address these problems, this paper presents a hybrid approach, which combines background segmentation and long-term tracking with selective tracking and reducing search area, we robustly and effectively detect the foreground objects. The evaluation of realistic sequences from i-LIDS dataset shows that the proposed methodology outperforms with most of the state-of-the-art methods.

Original languageEnglish
Title of host publicationProceedings - 11th International Conference on Frontiers of Information Technology, FIT 2013
Pages13-18
Number of pages6
DOIs
StatePublished - 2013
Event11th International Conference on Frontiers of Information Technology, FIT 2013 - Islamabad, Pakistan
Duration: 16 Dec 201318 Dec 2013

Publication series

NameProceedings - 11th International Conference on Frontiers of Information Technology, FIT 2013

Conference

Conference11th International Conference on Frontiers of Information Technology, FIT 2013
Country/TerritoryPakistan
CityIslamabad
Period16/12/1318/12/13

Keywords

  • Foreground detection
  • Selective tracking
  • Visual surveillance

Fingerprint

Dive into the research topics of 'Foreground object detection and tracking for visual surveillance system: A hybrid approach'. Together they form a unique fingerprint.

Cite this