Background modeling using mixture of Gaussians and Laplacian pyramid decomposition

We propose an effective background model using mixture of Gaussians and Laplacian pyramid decomposition for foreground object segmentation from complex scene containing stationary and moving objects. The Laplacian pyramid is employed to decompose the input image into a low-frequency big scale image and a high-frequency image. We build two mixtures of Gaussians in each pixel to represent the statistical characteristics of the stationary and moving points with proper feature vectors. Big scale foreground objects are obtained by fusing the results from stationary and dynamic models. Original foreground objects are then restored using the established model, low-frequency and high-frequency images. The experiments we performed here on complex scenes containing dynamic background objects have showed better performance and less memory cost compared.