We use sequence from the category dynamic backgrounds of the ChangeDetection.net dataset (2012 Dataset).
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.