The Open Automation and Control Systems Journal

2013, 5 : 113-118
Published online 2013 November 29. DOI: 10.2174/1874444301305010113
Publisher ID: TOAUTOCJ-5-113

Surveillance Video Synopsis Based on Moving Object Matting Using Noninteractive GrabCut

Jianrong Cao , Xuemei Sun and Lili Hao
Department of Information and Electrical Engineering, Shandong Jianzhu University, Jinan, Shandong 250101, China.

ABSTRACT

An algorithm of surveillance video synopsis is presented in this paper. At first, the detection method of moving object for surveillance video is proposed. Then the ROI (Region of Interest) of moving object is extracted and a noninteractive matting algorithm of moving object based on GrabCut is presented. These matting moving objects are placed without overlapping in a background image, so a frame that several moving objects have been placed in a background image can be obtained. Finally, a series of these frame images can be obtained in timeline and a single camera surveillance video synopsis can be formed. The experimental results show that our detection method of moving object is superior to those methods such as Gaussian mixture model, background subtraction, frame difference method and Li’s method. The synopsis obtained contains all objects appeared in surveillance video and is a concise expression for original video.

Keywords:

Video monitoring, Background modeling, Object detection.