Page 37 - Read Online

Page 30 Xu et al. J Surveill Secur Saf 2020;1:16-33 I http://dx.doi.org/10.20517/jsss.2020.04

Figure 14. Comparison of errors of different field removal methods

Table 4. Statistical table of crime identification accuracy (%)
Crime identification accuracy Crime identification accuracy Crime identification accuracy
No. rate (%) No. rate (%) No. rate (%)
1 84 21 92 41 85
2 92 22 89 42 89
3 84 23 91 43 87
4 84 24 84 44 94
5 82 25 90 45 93
6 86 26 83 46 80
7 91 27 92 47 82
8 82 28 85 48 86
9 87 29 82 49 91
10 82 30 85 50 95
11 82 31 92 51 92
12 88 32 93 52 94
13 87 33 88 53 93
14 83 34 86 54 85
15 92 35 84 55 93
16 90 36 89 56 90
17 94 37 90 57 90
18 85 38 88 58 95
19 92 39 87 59 83
20 82 40 88 60 83

the occurrence of anomalies was detected, and the location algorithm of the escape center was studied.
Firstly, the algorithm to detect the single escape center was implemented. To further detect the possible
location of anomalies in the actual scene, based on the single escape center, further research was conducted
to obtain multiple localization algorithms for the escape center. Many experiments were performed on the
synthetic data and the UMN public dataset. The experiments show that the algorithm based on the multi-
escape center is accurate in different scenarios.