Texture-based self-adaptive moving object detection technique for complex scenes. (August 2018)

• Record Type: Journal Article
• Authors: Goyal, Kalpana; Singhai, Jyoti
• Is Part Of: Computers & electrical engineering. Volume 70(2018)
• Page Start: 275
• Page End: 283
• Publication Date: 2018-08
• Subjects: Background subtraction -- Background modeling -- Local binary pattern -- Texture -- Moving object detection -- Segmentation; Computer engineering -- Periodicals; Electrical engineering -- Periodicals; Electrical engineering -- Data processing -- Periodicals; Ordinateurs -- Conception et construction -- Périodiques; Électrotechnique -- Périodiques; Électrotechnique -- Informatique -- Périodiques; Computer engineering; Electrical engineering; Electrical engineering -- Data processing; Periodicals; Electronic journals; 621.302854
• DOI: 10.1016/j.compeleceng.2016.05.017
• Languages: English
• ISSNs: 0045-7906

Abstract

Highlights: Moving object detection method is proposed based on texture features. This method uses Local Binary Pattern (LBP) as measure of texture. Adaptive learning rate is used to deal with different rates of change in background. It can handle strong dynamic background, sudden and gradual illumination variations. Graphical abstract: Abstract: Moving object detection is a fundamental and critical task in video surveillance systems. It is very challenging for complex scenes having dynamic background and illumination variations. In this paper, Local Binary Pattern (LBP) texture-based moving object detection algorithm is proposed which uses adaptive learning rate to deal with different rates of change in background. This algorithm deals with the strong dynamic background and illumination variations effectively. The performance of the proposed algorithm is evaluated on the challenging videos containing strong dynamic background and illumination variations using standard performance metrics. Experimental results show that the proposed method achieves more than 10% average improvement in accuracy compared over existing algorithms.