Laser & Optoelectronics Progress, Volume. 57, Issue 4, 041010(2020)
Forest Fire Detection Method Based on Transfer Learning of Convolutional Neural Network
Figures & Tables(8)
Fig. 5. Forest fire test results. (a) Test results ①; (b) test results ②; (c) test results ③; (d) test results ④
Table 1. Classification performances of different models
View tableTable 1. Classification performances of different models
Model Training accuracy /% Classification performance /% Model 1 93.7 86.0 Model 2 96.6 93.6 Model 3 98.9 98.3
Table 2. Comparison of different CNN algorithms
View tableTable 2. Comparison of different CNN algorithms
Method Detectable rate /% Precision /% SPP YOLO SSD Model A 99 98.6 99.8 86 93.9 96 94 80 Model B 99.8 97
Table 3. Comparison of different migration learning CNN algorithms
View tableTable 3. Comparison of different migration learning CNN algorithms
Method Detectable rate /% Precision /% Time /s VGG 98.9 96.3 2.03 AlexNet 99.8 97.0 1.78
Tools
Get Citation
Copy Citation Text
Yajie Fu, Hongli Zhang. Forest Fire Detection Method Based on Transfer Learning of Convolutional Neural Network[J]. Laser & Optoelectronics Progress, 2020, 57(4): 041010
Paper Information
Category: Image Processing
Received: May. 31, 2019
Accepted: Aug. 12, 2019
Published Online: Feb. 20, 2020
The Author Email: Zhang Hongli (zhlxju@163.com)
© Copyright 2018-2021 | Chinese Laser Press.
All Rights Reserved 沪ICP备15018463号-20