Fast moving object detection using improved Gaussian mixture models

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

8 Citations (Scopus)

Abstract

Gaussian mixture models(GMM) is a widely used approach for background modeling. However, computational barriers have limited its usage in real-time video processing applications. In this paper, we discussed a new update algorithm to achieve the goal of fast detection. Dirichlet prior are introduced to avoid redundant Gaussian components, reducing the computation time of each pixel. Most of the existing GMM based techniques use background/foreground data proportion, which is highly sensitive to the environment, to detect object. To avoid its possible negative effects on segmentation, we use sigmoid function to approximate the probability of Gaussian component belongs to the background and set a threshold for it to segment. Experimental results show this method leads to a faster and a better segmentation than traditional GMM.

Original languageEnglish
Title of host publicationICALIP 2014 - 2014 International Conference on Audio, Language and Image Processing, Proceedings
EditorsWanggen Wan, Fa-Long Luo, Xiaoqing Yu
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages501-505
Number of pages5
ISBN (Electronic)9781479939022
DOIs
Publication statusPublished - 13 Jan 2015
Externally publishedYes
Event4th International Conference on Audio, Language and Image Processing, ICALIP 2014 - Shanghai, China
Duration: 7 Jul 20149 Jul 2014

Publication series

NameICALIP 2014 - 2014 International Conference on Audio, Language and Image Processing, Proceedings

Conference

Conference4th International Conference on Audio, Language and Image Processing, ICALIP 2014
Country/TerritoryChina
CityShanghai
Period7/07/149/07/14

Keywords

  • adaptive Gaussian mixture
  • dirichlet prior
  • moving object detection
  • sigmoid function

Fingerprint

Dive into the research topics of 'Fast moving object detection using improved Gaussian mixture models'. Together they form a unique fingerprint.

Cite this