Detection Method for Video Flame Super-Pixel Based on Optimized InceptionV1

Fig. 9. Detection results of flame super-pixel. (a) Original image; (b) video super-pixel segmentation result; (c) full-frame detection result; (d) final detection result of removing non-flame area

Download full size

Fig. 10. Ground truth annotation image

Download full size

Fig. 11. Partial flame detection results of proposed method. (a) Image 1; (b) image 2; (c) image 3; (d) image 4; (e) image 5; (f) image 6

Download full size

Table 1. Flame image data source and quantity
View table
Table 1. Flame image data source and quantity
Dataset Quantity
ImageNet dataset 3067
Bilkent University Fire dataset 4782
Durham University Fire dataset 4563
Non-fire dataset 5439

Table 2. Results of ablation experiments
View table
Table 2. Results of ablation experiments
Imp-A Imp-B Focal-Loss FLOPS/10⁹ Test accuracy /%
1.502 94.82
√ 1.502 95.09
√ √ 1.232 96.23
√ 1.232 95.87
√ 1.467 95.24
√ √ 1.467 96.12
√ √ 1.197 96.56
√ √ √ 1.197 97.01

Table 3. Comparison of index evaluation of different methods
View table
Table 3. Comparison of index evaluation of different methods
Method TPR FPR A P F1-score
AlexNet 0.91 0.19 0.88 0.92 0.91
VGG-16^[7] 0.92 0.12 0.90 0.93 0.92
InceptionV1 0.94 0.09 0.95 0.95 0.94
Proposed method 0.96 0.08 0.95 0.95 0.95

Table 4. Evaluation and comparison of network computing performance
View table
Table 4. Evaluation and comparison of network computing performance
Method C /10⁶ A /% A∶C FPS
AlexNet 72.0 91.7 1.27 20.1
VGG-16 215.3 92.6 1.36 13.8
InceptionV1 6.1 95.2 15.60 40.7
Ref. [20] \ \ \ 14.2
Ref. [19] \ \ \ 3.9
Proposed method 1.8 95.4 53.00 108.4

Table 5. Performance evaluation results of flame detection model

View table

Table 5. Performance evaluation results of flame detection model

Method	TPR	FPR	F1-score	P	A
SEEDS+AlexNet	0.86	0.29	0.84	0.83	0.86
SEEDS+VGG16	0.85	0.31	0.82	0.80	0.85
SEEDS+InceptionV1	0.94	0.18	0.92	0.91	0.94
Ref. [20]	0.91	0.13	0.88	0.86	0.87
Ref. [19]	0.87	0.17	0.88	0.90	0.90
Proposed method	0.94	0.04	0.94	0.95	0.96

Table 6. Evaluation results of flame localization performance
View table
Table 6. Evaluation results of flame localization performance
Method TPR F1-score P S
SEEDS+AlexNet 0.80 0.78 0.76 0.78
SEEDS+VGG16 0.85 0.84 0.84 0.76
SEEDS+InceptionV1 0.90 0.88 0.87 0.87
Proposed method 0.91 0.90 0.89 0.90

Tools

Get Citation

Copy Citation Text

Jun Deng, Hanwen Yao, Weifeng Wang, Zhao Li, Ce Liang. Detection Method for Video Flame Super-Pixel Based on Optimized InceptionV1[J]. Laser & Optoelectronics Progress, 2021, 58(2): 0210004

Download Citation

EndNote(RIS)BibTex Plain Text

Set citation alerts for article

Save article for my favorites