Enhanced moving object detection using tracking system for video surveillance purposes

Axel Beaugendre, Chenyuan Zhang, Jiu Xu, Satoshi Goto

Research output: Chapter in Book/Report/Conference proceedingConference contribution

2 Citations (Scopus)

Abstract

Foreground extraction and moving object detection are often used in human tracking systems. However those methods are not able to produce accurate results when objects are too close or when occlusions happen since the result is generally a single big blob which contains all the different objects. In this paper we propose a novel and efficient moving object detection enhancement method. Indeed, by using the results of the previous iteration tracking we are able to keep a correct number of moving objects by removing useless blobs and by splitting those which contain more than one tracker. The method can also speed up the tracking by creating a link between a tracker and a blob to avoid unnecessary processing in some situations.

Original languageEnglish
Title of host publication2012 IEEE Visual Communications and Image Processing, VCIP 2012
DOIs
Publication statusPublished - 2012
Event2012 IEEE Visual Communications and Image Processing, VCIP 2012 - San Diego, CA
Duration: 2012 Nov 272012 Nov 30

Other

Other2012 IEEE Visual Communications and Image Processing, VCIP 2012
CitySan Diego, CA
Period12/11/2712/11/30

    Fingerprint

Keywords

  • detection
  • foreground
  • moving object
  • refinement
  • tracking

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition

Cite this

Beaugendre, A., Zhang, C., Xu, J., & Goto, S. (2012). Enhanced moving object detection using tracking system for video surveillance purposes. In 2012 IEEE Visual Communications and Image Processing, VCIP 2012 [6410776] https://doi.org/10.1109/VCIP.2012.6410776