bstract — Extracting moving objects from background is a critical step for computer vision applications. GMM based algorithms have become the most commonly used technique for background subtraction in video sequence. However, it is not always easy to establish efficient and accurate background model with fast convergence rate. In this paper, an effective scheme was proposed to improve the convergence rate of Adaptive-K Gaussian Mixture Model (AKGMM). The AKGMM algorithm altered the dimension of the parameter space at each pixel adaptively according to the frequency of pixel value changes. The number of GMM reflected the complexity of pattern at the pixel. An adaptive learning rate was calculated for each Gaussian at every frame for speeding up the convergence without compromising model stability. Experimental results demonstrated that the proposed method gets a faster convergence while maintaining good robustness against complex environment compared to a conventional method.
