A background model re-initialization method based on sudden luminance change detection. (February 2015)

• Record Type: Journal Article
• Authors: Cheng, Fan-Chieh; Chen, Bo-Hao; Huang, Shih-Chia
• Is Part Of: Engineering applications of artificial intelligence. Volume 38(2015:Feb.)
• Page Start: 138
• Page End: 146
• Publication Date: 2015-02
• Subjects: Background model -- Sudden luminance change -- Entropy; Engineering -- Data processing -- Periodicals; Artificial intelligence -- Periodicals; Expert systems (Computer science) -- Periodicals; Ingénierie -- Informatique -- Périodiques; Intelligence artificielle -- Périodiques; Systèmes experts (Informatique) -- Périodiques; Artificial intelligence; Engineering -- Data processing; Expert systems (Computer science); Periodicals; 620.00285
• DOI: 10.1016/j.engappai.2014.10.023
• Languages: English
• ISSNs: 0952-1976

Abstract

Abstract: Sudden changes in illumination often occur in real world scenarios and may cause considerable difficulties in modeling backgrounds for the state-of-the-art background subtraction methods. In this paper, we propose a simple and effective background re-initialization method that detects sudden luminance change effectively. The purpose of the proposed method is not on the presentation of a specific solution for object detection, but is instead the improvement of the background subtraction approach so that it is capable of sudden luminance change adaptation. Two embodiments related to background subtraction, and which are based on the proposed method, are also presented. These embodiments can detect the moving objects accurately as the luminance of the background model is adjusted quickly after the proposed method is employed for generating the background model. Experimental results demonstrate that the proposed method effectively improves the background subtraction methods as measured by qualitative as well as quantitative assessments.