Moving object detection based on improved Gaussian mixture model
Zhiguo Bian, Xiaoshu Dong · 2012
Gaussian mixture model (GMM) has been widely used for robustly modeling complicated backgrounds. A novel algorithm which can effectively resolve the problems of disturbance caused by noise and illumination mutation is proposed in this paper. Edge Gaussian mixture model method is combined with improved Neighborhood-based difference method to solve these problems and improve the performance of moving object detection. Experimental results indicate that the proposed method has great capacity in restraining noise and dealing with illumination mutation, and it is more efficient and robust than the traditional methods. The proposed method provides a reliable basis to the phase of target tracking and categorization.