Fast Background Subtraction Using Improved GMM and Graph Cut

Citations Over TimeTop 14% of 2008 papers

Abstract

Background Subtraction is widely used to detect moving object from static background. In order to get good performance for practical application systems, the background subtraction method should not be too time and space consuming, and the accuracy is also required. Gaussian Mixture Model is a robust background subtraction method and has been widely used since it is proposed. Graph cut is a new algorithm developed to solve energy minimization problem and can be used to extract foreground object by constructing some appropriate energy functions. In this paper, an improved Gaussian Mixture Model is proposed to save time and space. And a new energy function is constructed for the graph cut. Space sampling is used to further accelerate the processing speed, so that it can be used in real-time applications. Shadow eliminating and noise removing method are also used to further improve the performance of the system. The experiment results demonstrate the efficiency of our method.

Related Papers

• → Robust background subtraction and maintenance(2004)43 cited
• → Efficient method for moving object detection in cluttered background using Gaussian Mixture Model(2014)18 cited
• → Student's t-distribution mixture background model for efficient object detection(2012)7 cited
• Parameter Analysis for Mixture of Gaussians Model(2006)
• → Commentary Paper 2 on "On Stable Dynamic Background Generation Technique Using Gaussian Mixture Models for Robust Object Detection'"(2008)1 cited