Page 41 - Read Online
P. 41

Page 139                         Tang et al. Intell Robot 2022;2(2):130­44  I http://dx.doi.org/10.20517/ir.2022.07



                    Clip1






                    Clip2


                               (a)          (b)         (c)          (d)          (e)          (f)

               Figure 5. The moving object detection experiments on the video Highway (Clip1) and People (Clip2): (a) the first frame; (b) the frame for
               detection; (c) the ground-truth; (d) the result of GMM; (e) the result of G-ViBe; and (f) the result of I-ViBe.


                            Table 3. The valuation of the three methods for moving objects detection on Highway and People

                            The valuation      The video clip1             The video clip2
                              indices   GMM  [32]  G-ViBe  [35]  I-ViBe  GMM  [32]  G-ViBe  [35]  I-ViBe
                            SP           0.8765  0.9910     0.9979  0.9998     0.9915   0.9992
                            RE           0.7843  0.8554     0.9674   0.1545    0.8616   0.9849
                            FPR          0.1234  0.0089     0.0020  0.0001     0.0084   0.0007
                            FNR          0.2156  0.1445     0.0325  0.8454     0.1383   0.0150
                            PWC          0.1307  0.0196     0.0041  0.0059     0.0097  0.0008
                            PRE          0.3532  0.8918     0.9713  0.8834     0.5110   0.8943
                            F            0.4871  0.8732     0.9694  0.2630     0.6415   0.9374




                    Clip1





                    Clip2

                              (a)          (b)          (c)          (d)          (e)          (f)

               Figure 6. The moving object detection experiments under challenging conditions: (a) the first frame; (b) the frame for detection; (c) the
               ground-truth; (d) the result of GMM; (e) the result of G-ViBe; and (f) the result of I-ViBe.


               combined with the edge information (see Figure 5 and Table 3). Furthermore, there are also ghost problems in
               the detection results of the experiment on People (Clip2) based on the G-ViBe, because the first frame includes
               the moving objects (see Figure 5e).


               4.3. The experiment under challenging conditions
               To further test the performance of the proposed method for moving object detection under some challenging
               conditions, two extensive experiments were conducted in the dataset of Fall (Clip1) and Boulevard (Clip2),
               respectively. In the Fall dataset, the background is changing obviously because of the leaves shaking violently.
               In the Boulevard dataset, the video is blurry due to the shake of the camera. The results of these experiments
               are shown in Figure 6 and Table 4.


               The results in the two experiments show that the performances of all the three methods decrease under dy-
   36   37   38   39   40   41   42   43   44   45   46