Acta Optica Sinica, Volume. 38, Issue 7, 0710001(2018)
Early Fire Detection Algorithm Based on ViBe and Machine Learning
Figures & Tables(8)
Fig. 2. ViBe motion test results. (a) Background model; (b) test results after background update; (c) test results of improved ViBe algorithm
Fig. 3. Foreground detection results. (a) Original image; (b) foreground area mask detected by algorithm in Ref. [12]; (c) foreground area mask detected by proposed algorithm
Table 1. Fire detection rate and response time tests of algorithm
View tableTable 1. Fire detection rate and response time tests of algorithm
Item Real fire video Experimental fire video V1 V2 V3 V4 V5 V6 V7 V8 TPR /% 87.5 91.6 90.2 82.5 98.2 95.4 96.3 93.6 FPR /% 0 0 0 0 0 0 0 0 Δ t 23.4 8.51 4.18 7.35 0.36 0.425 4.31 1.4 Δ t 34.34 9.45 4.29 11.75 0.45 0.51 5.12 1.52 Δ t 44.44 9.56 4.4 11.88 0.54 0.595 5.25 2.53 Δ t 54.55 9.66 4.51 12 0.63 0.68 5.36 2.63
Table 2. False positive rate test of algorithm
View tableTable 2. False positive rate test of algorithm
Item V9 V10 V11 V12 TNR/% 100 98.4 97.2 97.0 FNR/% 0 0 0 0 N =20 1 3 3 N =30 0 2 2 N =40 0 0 0 N =50 0 0 0
Tools
Get Citation
Copy Citation Text
Jianjun Mei, Wei Zhang. Early Fire Detection Algorithm Based on ViBe and Machine Learning[J]. Acta Optica Sinica, 2018, 38(7): 0710001
Paper Information
Category: Image Processing
Received: Dec. 19, 2017
Accepted: --
Published Online: Sep. 5, 2018
The Author Email: Mei Jianjun (tju_mei@163.com)
© Copyright 2018-2021 | Chinese Laser Press.
All Rights Reserved 沪ICP备15018463号-20