A Fuzzy Background Modeling Approach for Motion Detection in Dynamic Backgrounds

Introduction

Based on Type-2 Fuzzy Gaussian Mixture Model (T2-FGMM) and Markov Random Field (MRF), we propose a novel background modeling method for motion detection in dynamic scenes. The key idea of the proposed approach is the successful introduction of the spatial-temporal constraints into the T2-FGMM by a Bayesian framework. The evaluation results in pixel level demonstrate that the proposed method performs better than the Gaussian Mixture Model (GMM) [1] and T2-GMM [2] in such typical dynamic backgrounds as waving trees and water rippling.

Experimental Results

We use the "overpass" sequence of the ChangeDetection.net dataset to test the waving trees situation. Fig. 1 shows the input images, ground truth and the results of GMM, T2-FGMM and the proposed approach. The results show that our method can restrain the dynamic background better than GMM and T2-GMM. At the same time, the overall performance is better than GMM and T2-FGMM as well. We use the “canoe” sequence to test the water rippling situation. Fig. 2, shows the experimental results. Similar to the waving trees situation, our method can perform better than GMM and T2FGMM in both local and overall evaluations.

Fig. 1. The first row shows the original frames for the overpass sequence, the second row is the ground truth, the third row presents the results obtained by the GMM, the four row presents the results obtained by theT2-FGMM, the fith row presents the results obtained by the T2-FGMM-MRF.

Fig. 2. The first row shows the original frames for the canoe sequence, the second row is the ground truth, the third row presents the results obtained by the GMM, the four row presents the results obtained by theT2-FGMM, the fith row presents the results obtained by the T2-FGMM-MRF.

References

[1] C. Stauffer and W. Grimson, “Adaptive background mixture models for real-time tracking”, IEEE Conference on Computer Vision and Pattern Recognition, CVPR 1999, pp. 246-252, 1999

[2] F. El Baf, T. Bouwmans, B. Vachon, “Type-2 Fuzzy Mixture of Gaussians Model: Application to Background Modeling”, International Symposium on Visual Computing, ISVC 2008, pages 772-781, Las Vegas, USA, December 2008.

Publication

Z. Zhao, T. Bouwmans, X. Zhang, Y. Fang, “A Fuzzy Background Modeling Approach for Motion Detection in Dynamic Backgrounds”, International Conference on Multimedia and Signal Processing, Shanghai, China, December 2012

Source

The source is available on resquest at tbouwman at univ-lr.fr.