A Motion Detection Algorithm Integrating Foreground Matching into Gaussian Mixture Modeling

In conventional Gaussian Mixture Modeling (GMM), the risk that foreground models convert into background models increases with the accumulation of the foreground model's weight under a constant learning rate. That makes the conventional GMM unable to deal with slow moving objects. This paper proposes a motion detection algorithm which fuses foreground matching into the conventional GMM. The motion information contained in foreground models is obtained by checking in real-time the state of each pixel. Foreground matching enables the GMM to deal with indistinguishable moving objects and greatly improves its tolerance to slow moving objects. The quantitative evaluation and comparison show that the proposed algorithm outperforms the conventional GMM by detecting up to 23.3% of true positives with an acceptable cost of time consumption and the number of false detections.

[1]  Fenghua Zhu,et al.  A survey of vision-based vehicle detection and tracking techniques in ITS , 2013, Proceedings of 2013 IEEE International Conference on Vehicular Electronics and Safety.

[2]  Sos S. Agaian,et al.  Comparison Study of Gaussian Mixture Models for Fingerprint Image Duplication with a New Model , 2016, Image Processing: Algorithms and Systems.

[3]  Takeo Kanade,et al.  A System for Video Surveillance and Monitoring , 2000 .

[4]  Wei Liu,et al.  Effective background modelling and subtraction approach for moving object detection , 2015, IET Comput. Vis..

[5]  A. Utasi,et al.  Reducing the Foreground Aperture Problem in Mixture of Gaussians Based Motion Detection , 2007, 2007 14th International Workshop on Systems, Signals and Image Processing and 6th EURASIP Conference focused on Speech and Image Processing, Multimedia Communications and Services.

[6]  Kentaro Toyama,et al.  Wallflower: principles and practice of background maintenance , 1999, Proceedings of the Seventh IEEE International Conference on Computer Vision.

[7]  N. K. Kamila,et al.  Slow and Fast Moving Object Detection under Illumination Variation Condition , 2013 .

[8]  U. K. Jaliya,et al.  A Survey on Object Detection and Tracking Methods , 2014 .

[9]  Mohan M. Trivedi,et al.  Looking at Vehicles on the Road: A Survey of Vision-Based Vehicle Detection, Tracking, and Behavior Analysis , 2013, IEEE Transactions on Intelligent Transportation Systems.

[10]  Deyun Xiao,et al.  Review on vehicle detection based on video for traffic surveillance , 2008, 2008 IEEE International Conference on Automation and Logistics.

[11]  A NiranjilKumar,et al.  Background Subtraction in Dynamic Environment based on Modified Adaptive GMM with TTD for Moving Object Detection , 2015 .

[12]  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).