Investigation of mixture of Gaussians method for background subtraction in traffic surveillance

Many background subtraction techniques have been developed in the past years to improve the precision of motion detection in video surveillance systems. Separating the moving objects from the background is a goal in every modern video surveillance system. Mixture of Gaussians (MoG) is one of the most complex methods used for motion detection in video sequences. This paper further investigates the MoG method. The algorithm is implemented in MATLAB and a typical traffic video is estimated. The accuracy of the algorithm is measured as a function of each variable parameter. An optimal set of parameters along with a filter are proposed in order to increase the performance.

[1]  Thierry Bouwmans,et al.  Background Modeling using Mixture of Gaussians for Foreground Detection - A Survey , 2008 .

[2]  Atsushi Shimada,et al.  Spatial-Temporal Integration of Adaptive Gaussian Mixture Background Models , 2008 .

[3]  Reinhard Klette,et al.  Parameter Analysis for Mixture of Gaussians Model , 2006 .

[4]  Xinhua He,et al.  Adaptive Gaussian mixture learning for moving object detection , 2010, 2010 3rd IEEE International Conference on Broadband Network and Multimedia Technology (IC-BNMT).

[5]  Dan Roth,et al.  Learning to detect objects in images via a sparse, part-based representation , 2004, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[6]  Hongbin Wang,et al.  Regularized online Mixture of Gaussians for background subtraction , 2011, 2011 8th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS).

[7]  Karen Das,et al.  An Adaptive GMM Approach to Background Subtraction for Application in Real Time Surveillance , 2013, ArXiv.

[8]  Atsushi Shimada,et al.  Dynamic Control of Adaptive Mixture-of-Gaussians Background Model , 2006, 2006 IEEE International Conference on Video and Signal Based Surveillance.

[9]  W. Eric L. Grimson,et al.  Background Subtraction for Temporally Irregular Dynamic Textures , 2008, 2008 IEEE Workshop on Applications of Computer Vision.

[10]  Andrew Hunter,et al.  Scene modelling using an adaptive mixture of Gaussians in colour and space , 2005, IEEE Conference on Advanced Video and Signal Based Surveillance, 2005..

[11]  W. Eric L. Grimson,et al.  Adaptive background mixture models for real-time tracking , 1999, Proceedings. 1999 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No PR00149).