Abandoned Objects Detection Using Double Illumination Invariant Foreground Masks

This paper proposes an automatic and robust method to detect and recognize the abandoned objects for video surveillance systems. Two Gaussian Mixture Models(Long-term and Short-term models) in the RGB color space are constructed to obtain two binary foreground masks. By refining the foreground masks through Radial Reach Filter(RRF) method, the influence of illumination changes is greatly reduced. The height/width ratio and a linear SVM classifier based on HOG (Histogram of Oriented Gradient) descriptor is also used to recognize the left-baggage. Tests on datasets of PETS2006, PETS2007 and our own videos show that the proposed method in this paper can detect very small abandoned objects within low quality surveillance videos, and it is also robust to the varying illuminations and dynamic background.

[1]  Yuri Ivanov,et al.  Robust Abandoned Object Detection Using Dual Foregrounds , 2008, EURASIP J. Adv. Signal Process..

[2]  Xingzhi Luo,et al.  A Multiscale Parametric Background Model for Stationary Foreground Object Detection , 2007, 2007 IEEE Workshop on Motion and Video Computing (WMVC'07).

[3]  Michael D. Beynon,et al.  Detecting abandoned packages in a multi-camera video surveillance system , 2003, Proceedings of the IEEE Conference on Advanced Video and Signal Based Surveillance, 2003..

[4]  Chih-Jen Lin,et al.  LIBSVM: A library for support vector machines , 2011, TIST.

[5]  Wen-Hao Wang,et al.  An Abandoned Objects Management System Based on the Gaussian Mixture Model , 2008, 2008 International Conference on Convergence and Hybrid Information Technology.

[6]  Yutaka Satoh,et al.  Robust object detection using a Radial Reach Filter (RRF) , 2004 .

[7]  Lisa M. Brown,et al.  View independent vehicle/person classification , 2004, VSSN '04.

[8]  Dragoljub Pokrajac,et al.  Detecting and Recognizing Abandoned Objects in Crowded Environments , 2008, ICVS.

[9]  Carlos Orrite-Uruñuela,et al.  Automatic left luggage detection and tracking using multi-camera ukf , 2006 .

[10]  Bill Triggs,et al.  Histograms of oriented gradients for human detection , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[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).