Real-time background modeling based on a multi-level texture description

Chia Hung Yeh, Chih Yang Lin*, Kahlil Muchtar, Li Wei Kang

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

Abstract

Background construction is the base of object detection and tracking of machine vision systems. Traditional background modeling methods often require complicated computations and are sensitive to illumination changes. This paper proposes a novel block-based background modeling method based on a hierarchical coarse-to-fine texture description, which fully utilizes the texture characteristics of each incoming frame. The proposed method is efficient and can resist both illumination changes and shadow disturbance. The experimental results show that this method is suitable for real-world scenes and real-time applications.

Original languageEnglish
Pages (from-to)106-127
Number of pages22
JournalInformation Sciences
Volume269
DOIs
Publication statusPublished - 2014 Jun 10
Externally publishedYes

Keywords

  • Background modeling
  • Gaussian mixture modeling
  • Motion detection

ASJC Scopus subject areas

  • Software
  • Control and Systems Engineering
  • Theoretical Computer Science
  • Computer Science Applications
  • Information Systems and Management
  • Artificial Intelligence

Fingerprint

Dive into the research topics of 'Real-time background modeling based on a multi-level texture description'. Together they form a unique fingerprint.

Cite this