Improving Mixture of Gaussians background model through adaptive learning and Spatio-Temporal voting
The Mixture of Gaussians (MoG) is a frequently used method for foreground-background separation. Although it is quite capable of handling gradual illumination changes and multi-model background, it cannot cope with dynamic changes such as the presence of paused objects, shadows, and sudden illumination changes. Furthermore, it is a parametric model and in general, its parameter tuning for different scenes remains a manual effort. In this paper, we propose an online learning framework that tackles these issues. Our main contributions are: local adaptive parameter learning, a feedback based updating method for stopped objects, hierarchical SURF features matching based ghosts suppression, and a new sudden illumination detection and handling technique. The proposed model is rigorously tested and compared with several previous models and has shown significant performance improvements.