Page 42 - Read Online
P. 42

Tang et al. Intell Robot 2022;2(2):130­44  I http://dx.doi.org/10.20517/ir.2022.07  Page 140

                          Table 4. The valuation of the three methods for moving object detection under challenging conditions

                            The valuation      The video Clip1             The video Clip2
                               indices  GMM  [32]  G-ViBe  [35]  I-ViBe  GMM  [32]  G-ViBe  [35]  I-ViBe
                            SP           0.9547  0.8765     0.9960  0.9850     0.9025   0.9974
                            RE           0.8755  0.7496     0.7184  0.8643     0.9258   0.9574
                            FPR          0.0452  0.1234     0.0039   0.0149    0.0974  0.0025
                            FNR          0.1244  0.2503     0.2815   0.1356    0.0741   0.0425
                            PWC          0.0481  0.1285     0.0106   0.0219    0.0957   0.0051
                            PRE          0.4245  0.2016     0.8202   0.7819    0.4173   0.9617
                            F            0.5718  0.3178     0.7659   0.8210    0.5753   0.9595








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

               Figure 7. The moving object detection experiments on the video Fall: (a) the first frame; (b) the frame for detection; (c) the ground-truth;
               d) the result of G-ViBe; (e) the result of F-ViBe; and (f) the result of I-ViBe.


               namicenvironments. Themainreasonisthatallthethreemethodsarebasedonthemechanismofbackground
               subtraction. However, the performance of the proposed approach does not decrease dramatically compared
               with other two methods (see the values of PRE and F in Table 4). This performance of the proposed approach
               is very important for the real application of moving object detection.



               5. DISCUSSION
               The results presented in Section 3 show that the proposed approach can deal with the ghost area problem and
               remove the shadow very well. In addition, the evaluation indices of the proposed approach are better than the
               GMM method and the general ViBe method. In this section, some performances of the proposed approach
               are discussed, including the computation complexity and the background updating mechanism.


               One key part of the ViBe-based approach is the background updating mechanism, so the performance of the
               improvement in this part for the proposed method is discussed first. An experiment was conducted in the
               dataset of Fall, where the proposed approach was compared with two methods. The first one is the general
               ViBe. The second one is a method which has the same parameters and work flow as the proposed approach,
               except that the background updating mechanism is based on the fixed detection radius and updating rate,
               and this method is called F-ViBe. The experimental results of Section 3.3 are used as reference, as shown in
               Figure 7 and Table 5. The experimental results show that the proposed approach can deal with the dynamic
               environment better than the other two methods. Thus, the background updating mechanism is very efficient
               for moving object detection under complex environment. In addition, the detection radius and updating rate
               of the F-ViBe method are given by the designer, which need more experience and time.


               Another important index of the moving object detection method is the real time problem, because the speed of
               the moving object is very high sometimes. The proposed approach has two main differences with the general
               ViBe method, the background modeling and updating mechanism and the shadow removal strategy. Thus,
               the time needed in all the three experiments of Clip1 in Section 3 is divided into two parts, the time for the
               background modeling and the time for moving object detection (including background updating).
   37   38   39   40   41   42   43   44   45   46   47