Title :
A robust hybrid movement detection method in dynamic background
Author :
Fazli, Saeid ; Pour, Hamed Moradi ; Bouzari, Hamed
Author_Institution :
Electr. Eng. Dept., Zanjan Univ., Zanjan
Abstract :
Motion segmentation is a very critical task in video surveillance system. In this paper, we propose a novel approach to detect moving objects in a complex background. Gaussian mixture model (GMM) is an effective way to extract moving objects from a video sequence. However, the conventional mixture Gaussian method suffers from false motion detection in complex backgrounds and slow convergence. This work, in order to achieve robust and accurate extraction of the shapes of moving objects, applies a hybrid method to remove noise from images. The proposed model consists of two stages. The first stage consists of a fourth order PDE and the second stage is a relaxed median filter, which processes the output of fourth order PDE. Experimental results show that the proposed model performs well even in the presence of higher levels of noise.
Keywords :
Gaussian processes; feature extraction; image denoising; image motion analysis; image segmentation; image sequences; median filters; object detection; partial differential equations; shape recognition; video signal processing; video surveillance; GMM; Gaussian mixture model; dynamic complex background; fourth order PDE; motion segmentation; moving object detection; noise removal; relaxed median filter; robust hybrid movement detection; shape extraction; video sequence; video surveillance system; Computer vision; Convergence; Motion detection; Motion segmentation; Noise robustness; Noise shaping; Object detection; Shape; Video sequences; Video surveillance;
Conference_Titel :
Electrical Engineering/Electronics, Computer, Telecommunications and Information Technology, 2009. ECTI-CON 2009. 6th International Conference on
Conference_Location :
Pattaya, Chonburi
Print_ISBN :
978-1-4244-3387-2
Electronic_ISBN :
978-1-4244-3388-9
DOI :
10.1109/ECTICON.2009.5137244