Title :
Motion detection based on background model
Author :
Qiang Zhai ; Zhenjiang Miao ; Qiang Zhang
Author_Institution :
Inst. of Inf. Sci., Beijing Jiaotong Univ., Beijing, China
Abstract :
Motion object detection is a very important part of Video Surveillance System. In this paper we provide a new modeling approach based on color, neighborhood feature to solve the shortage of the traditional Gaussian mixture model (GMM) on motion detection. Firstly, we build the initial GMM based on pixel color information and obtain initial parameters and initial detection result. Then we extract the gradient and modified local binary pattern (lbp) feature and build new GMM to achieve accurate detection result. Moreover, we use a unique voting strategy during the foreground pixel detection. We testify out approach in indoor and outdoor environment, the implement results show that our approach can remove the influence of illumination and camera shaking.
Keywords :
Gaussian processes; gradient methods; image colour analysis; image motion analysis; mixture models; object detection; video signal processing; video surveillance; GMM; Gaussian mixture model; LBP feature; background model; foreground pixel detection; gradient feature; indoor environment; modified local binary pattern feature; motion object detection; neighborhood feature; outdoor environment; pixel color information; video surveillance system; voting strategy; Clolor information; GMM; Gradient; LBP;
Conference_Titel :
Wireless, Mobile and Multimedia Networks (ICWMMN 2013), 5th IET International Conference on
Conference_Location :
Beijing
Electronic_ISBN :
978-1-84919-726-7
DOI :
10.1049/cp.2013.2409