Localized adaptive learning of Mixture of Gaussians models for background extraction

The Mixture of Gaussians (MoG) background subtraction model is one of the most popular methods for segmenting moving objects in videos. However, to achieve satisfactory background subtraction results, its parameters need to be hand-tuned specifically for each scenario. This becomes a major obstacle for this model to be employed in real-time applications. This paper proposes a self-adaptive method for tuning of the parameters of Mixture of Gaussians (MoG) background model based on the local intensity changes. To cope with different motion patterns in different regions of a video frames, we have introduced a local parameters for each pixel in the frame. The robustness of the proposed method is tested on a variety of complex data-sets. It can be seen from the result that, despite its simplicity, the proposed model has achieved significant improvements compared to the standard model.