A novel GMM-based motion segmentation method for complex background

Segmentation of moving objects in image sequences is a fundamental step in many computer vision applications such as visual surveillance and robot vision. 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. A novel approach, which combines a modified adaptive GMM for background subtraction and Neighborhood-based difference and Overlapping-based classification method in order to achieve robust and accurate extraction of the shapes of moving objects is introduced in this paper. Finally, experimental results and a performance measure establishing the confidence of the method are presented.