Probabilistic BPRRC: Robust Change Detection against Illumination Changes and Background Movements

Kentaro YOKOI  

Publication
IEICE TRANSACTIONS on Information and Systems   Vol.E93-D   No.7   pp.1700-1707
Publication Date: 2010/07/01
Online ISSN: 1745-1361
DOI: 10.1587/transinf.E93.D.1700
Print ISSN: 0916-8532
Type of Manuscript: Special Section PAPER (Special Section on Machine Vision and its Applications)
Category: 
Keyword: 
change detection,  background detection,  Probabilistic BPRRC,  robust,  illumination changes,  background movements,  

Full Text: PDF>>
Buy this Article




Summary: 
This paper presents Probabilistic Bi-polar Radial Reach Correlation (PrBPRRC), a change detection method that is robust against illumination changes and background movements. Most of the traditional change detection methods are robust against either illumination changes or background movements; BPRRC is one of the illumination-robust change detection methods. We introduce a probabilistic background texture model into BPRRC and add the robustness against background movements including foreground invasions such as moving cars, walking people, swaying trees, and falling snow. We show the superiority of PrBPRRC in the environment with illumination changes and background movements by using three public datasets and one private dataset: ATON Highway data, Karlsruhe traffic sequence data, PETS 2007 data, and Walking-in-a-room data.