Forest Fire Recognition by Improved EfficientNet-E Model Based on ECA Attention Mechanism

doi:10.12141/j.issn.1000-565X.230046

Abstract

Abstract:

The occurrence of fires has brought huge losses to society. The task of forest fire prevention and control is becoming increasingly urgent, and global warming has made this problem more complicated. Deep learning plays an important role in all walks of life. A large number of models are constantly designed and proposed, and there are various ways to improve the models. Therefore, this article proposed the EfficientNet-E model, which uses the more advanced ECA module (Efficient Channel Attention module) to replace the SE module in the EfficientNet. It improves the performance of the model by enhancing the performance of the attention mechanism. Compared with the SE module, the ECA module better retains the information during transmission, allowing the data features to be more fully retained during the transmission process, thus enabling the model to be optimized. To verify the performance of the EfficientNet-E model and the advantages of EfficientNet’s design idea in forest fire identification compared with traditional models, this article selected representatives of classic models, ResNet and DenseNet, as comparison references, and conducted related experiments in combination with EfficientNet and EfficientNet-E.The experiment selected 3 303 forest fire, non-fire and smoke pictures.The results of multiple rounds of tests show that EfficientNet-E is better than the conventional classic deep learning model in identifying forest fire data, and compared with the original EfficientNet’s average accuracy of 89.28%, EfficientNet-E’s average accuracy (90.04%) is obviously improved. The standard deviation is smaller and the training stability is better, which confirms the improved EfficientNet-E’s better performance.

Key words: deep learning, image recognition, forest fire, EfficientNet-E, attention mechanism

CLC Number:

TP18

ZHOU Lang, FAN Kun, QU Hua, et al. Forest Fire Recognition by Improved EfficientNet-E Model Based on ECA Attention Mechanism[J]. Journal of South China University of Technology(Natural Science Edition), 2024, 52(2): 42-49.

Figures/Tables 14

Fig.1

Fig.2

Fig.3

Fig.4

Fig.5

Fig.6

Fig.7

Fig.8

Fig.9

Table 1

EfficientNet-E model parameters"

阶段	操作	数据宽 $×$ 高	通道数	层数	卷积步长
1	Conv3 $×$ 3	224 $×$ 224	32	1	2
2	MBConv1，k3 $×$ 3	112 $×$ 112	16	1	1
3	MBConv6，k3 $×$ 3	112 $×$ 112	24	2	2
4	MBConv6，k5 $×$ 5	56 $×$ 56	40	2	2
5	MBConv6，k3 $×$ 3	28 $×$ 28	80	3	2
6	MBConv6，k5 $×$ 5	14 $×$ 14	112	3	1
7	MBConv6，k5 $×$ 5	14 $×$ 14	192	4	2
8	MBConv6，k3 $×$ 3	7 $×$ 7	320	1	1
9	Conv1×1&Pooling&FC	7 $×$ 7	1 280	1

Table 1

Fig.10

Table 2

Fig.11

Fig.12

References 17

1	赵鹏武，武峻毅，张恒．基于聚类分析法的我国森林火险等级区划研究［J］．林业工程学报，2021，6（3）：142-148.
	ZHAO Pengwu， WU Junyi， ZHANG Heng ．Study on forest fire risk classification in China using cluster analysis［J］．Journal of Forestry Engineering，2021，6（3）：142-148.
2	祖鑫萍，李丹．基于无人机图像和改进YOLOv3-SPP算法的森林火灾烟雾识别方法［J］．林业工程学报，2022，7（5）：142-149.
	ZU Xinping， LI Dan ．Research on forest fire smoke identification method based on UAV images and improved YOLOv3-SPP algorithm［J］．Journal of Forestry Engineering，2022，7（5）：142-149.
3	杜嘉欣，常青，刘鑫．面向森林火灾烟雾识别的深度信念卷积网络［J］．现代电子技术，2020，43（13）：44-48.
	DU Jiaxin， CHANG Qing， LIU Xin ．DBN-CNN for forest fire smoke recognition［J］．Modern Electronics Technique，2020，43（13）：44-48.
4	李珍辉，鲁静文，陈镜伊，等．基于InceptionV3卷积神经网络森林火灾检测方法［J］．湖南工程学院学报（自然科学版），2021，31（4）：44-49.
	LI Zhen-hui， LU Jing-wen， CHEN Jing-yi，et al ．Forest fire detection method based on inception V3 convolutional neural network［J］．Journal of Hunan University of Engineering （Natural Science Edition），2021，31（4）：44-49.
5	李梁，董旭彬，赵清华．改进Mask R-CNN在航拍灾害检测的应用研究［J］．计算机工程与应用，2019，55（21）：167-176.
	LI Liang， DONG Xubin， ZHAO Qinghua ．Application research of improved Mask R-CNN in aerial disaster detection［J］．Computer Engineering and Applications，2019，55（21）：167-176.
6	周浪，樊坤，瞿华，等．基于Sparse-DenseNet模型的森林火灾识别研究［J］．北京林业大学学报，2020，42（10）：36-44.
	ZHOU Lang， FAN Kun， QU Hua，et al ．Forest fire identification based on Sparse-DenseNet model［J］．Journal of Beijing Forestry University，2020，42（10）：36-44.
7	李巨虎，范睿先，陈志泊．基于颜色和纹理特征的森林火灾图像识别［J］．华南理工大学学报（自然科学版），2020，48（1）：70-83.
	LI Juhu， FAN Ruixian， CHEN Zhibo ．Forest fire recognition based on color and texture features［J］．Journal of South China University of Technology （Natural Science Edition），2020，48（1）：70-83.
8	李惠鹏，李长勇，李贵宾，等．基于深度学习的多品种鲜食葡萄采摘点定位［J］．中国农机化学报，2022，43（12）：155-161.
	LI Huipeng， LI Changyong， LI Guibin，et al ．Picking point positioning of multi-variety table grapes based on deep-learning［J］．Journal of Chinese Agricultural Mechanization，2022，43（12）：155-161.
9	吴天赐，郁佳鑫，黄晓峰，等．深度学习图片分类模型ResNet-18用于判定口腔鳞状细胞癌浸润方式的初步研究［J］．口腔医学研究，2023，39（10）：917-922.
	WU Tianci， YU Jiaxin， HUANG Xiaofeng，et al ．Preliminary study on deep learning picture classification model for identification and classification of invasion pattern of oral squamous cell carcinoma［J］．Journal of Stomatology，2023，39（10）：917-922.
10	苏令涛，李瑞泽，张功磊，等．基于深度学习的农作物病虫害识别研究［J］．数学建模及其应用，2022，11（4）：1-12.
	SU Lingtao， LI Ruize， ZHANG Gonglei，et al ．Research on deep learning based crop pest and disease identification［J］．Mathematical Modeling and Its Application，2022，11（4）：1-12.
11	GOUR M， JAIN S， KUMAR T S ．Residual learning based CNN for breast cancer histopathological image classification［J］．International Journal of Imaging Systems and Technology，2020，30（3）：621-635.
12	WEINAN E， MA C， WU L ．A comparative analysis of optimization and generalization properties of two-layer neural network and random feature models under gradient descent dynamics［J］．Science China Mathematics，2020，63（7）：1235-1265.
13	TAN M， LE Q V ．EfficientNet：rethinking model scaling for convolutional neural networks［C］∥Proceedings of the 36th International Conference on Machine Learning．Long Beach：ACM，2019：6105-6114.
14	尹梓睿，张索非，张磊，等．适于行人重识别的二分支EfficientNet网络设计［J］．信号处理，2020，36（9）：1481-1488.
	YIN Zirui， ZHANG Suofei， ZHANG Lei，et al ．Design of a two-branch EfficientNet for person re-identification［J］．Signal Processing，2020，36（9）：1481-1488.
15	叶冲，杨晶东．基于CBAM-EfficientNet的垃圾图像分类算法研究［J］．智能计算机与应用，2021，11（5）：218-222.
	YE Chong， YANG Jingdong ．Algorithm research on garbage image classification based on CBAM-EfficientNet［J］．Intelligent Computer and Application，2021，11（5）：218-222.
16	姜天宇，赵晓林，赵搏欣，等．基于EfficientNet的木薯叶病变自动分类模型［J］．计算机应用，2022，42（S1）：64-70.
	JIANG Tianyu， ZHAO Xiaolin， ZHAO Boxin，et al ．Automatic classification model for cassava leaf disease based on EfficientNet［J］．Computer Application，2022，42（S1）：64-70.
17	WANG Q， WU B， ZHU P，et al ．Supplementary material for ECA-Net：efficient channel attention for deep convolutional neural networks［C］∥Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition．Seattle，WA：IEEE，2020：13-19.

模型	训练时间均值/s	准确率均值/%	准确率标准差	训练稳定程度	单张图片预测时间/ms
ResNet-50	7 752	88.24	0.002 4	波动较大	11.32
DenseNet-121	9 122	89.13	0.005 3	波动较大	11.96
EfficientNet-B0	7 507	89.28	0.004 4	较为稳定	12.06
EfficientNet-E	7 725	90.04	0.002 1	较为稳定	12.03

[1]	YANG Chunling, LIANG Ziwen. Feature-Domain Proximal High-Dimensional Gradient Descent Network for Image Compressed Sensing [J]. Journal of South China University of Technology(Natural Science Edition), 2024, 52(3): 119-130.
[2]	ZHENG Juanyi, DONG Jiahao, ZHANG Qingjue, et al. Reconfigurable Intelligence Surface Channel Estimation Algorithm Based on RDN [J]. Journal of South China University of Technology(Natural Science Edition), 2024, 52(3): 102-111.
[3]	TIAN Sheng, SONG Lin, ZHAO Kailong. Point Cloud Classification Based on Offset Attention Mechanism and Multi-Feature Fusion [J]. Journal of South China University of Technology(Natural Science Edition), 2024, 52(1): 100-109.
[4]	LI Haiyan, YIN Haolin, LI Peng, et al.. Image Inpainting Algorithm Based on Dense Feature Reasoning and Mix Loss Function [J]. Journal of South China University of Technology(Natural Science Edition), 2023, 51(9): 99-109.
[5]	LI Fang, GUO Weisen, ZHANG Ping, et al.. Prediction Technique for Remaining Useful Life of Bearing Based on Spatial-Temporal Dual Cell State [J]. Journal of South China University of Technology(Natural Science Edition), 2023, 51(9): 69-81.
[6]	SU Jindian, YU Shanshan, HONG Xiaobin. A Self-Supervised Pre-Training Method for Chinese Spelling Correction [J]. Journal of South China University of Technology(Natural Science Edition), 2023, 51(9): 90-98.
[7]	LI Jiachun, LI Bowen, LIN Weiwei. AdfNet: An Adaptive Deep Forgery Detection Network Based on Diverse Features [J]. Journal of South China University of Technology(Natural Science Edition), 2023, 51(9): 82-89.
[8]	GUO Enqiang, FU Xinsha. Dropped Object Detection Method Based on Feature Similarity Learning [J]. Journal of South China University of Technology(Natural Science Edition), 2023, 51(6): 30-41.
[9]	ZHAO Jiandong, JIAO Lanxin, ZHAO Zhimin, et al. A Car-Following Model Driven by Combination of Theory and Data Considering Effects of Lane Change of Side Cars [J]. Journal of South China University of Technology(Natural Science Edition), 2023, 51(6): 10-19.
[10]	LU Lu, LAI Jinxiong. Smart Contract Vulnerability Detection Method Based on Capsule Network and Attention Mechanism [J]. Journal of South China University of Technology(Natural Science Edition), 2023, 51(5): 36-44.
[11]	YE Feng, CHEN Biao, LAI Yizong. Contrastive Knowledge Distillation Method Based on Feature Space Embedding [J]. Journal of South China University of Technology(Natural Science Edition), 2023, 51(5): 13-23.
[12]	LIU Yupeng, ZHANG Lei. Cognitive Diagnosis Model Integrating Forgetting and Importance of Knowledge Points [J]. Journal of South China University of Technology(Natural Science Edition), 2023, 51(5): 54-62.
[13]	ZHAO Rongchao, WU Baili, CHEN Zhuyun, WEN Kairu, ZHANG Shaohui, LI Weihua. Graph Neural Network for Fault Diagnosis with Multi-Scale Time-Spatial Information Fusion Mechanism [J]. Journal of South China University of Technology(Natural Science Edition), 2023, 51(12): 42-52.
[14]	HOU Liwei, WANG Hengsheng, ZOU Haoran. Deep Learning-Based Prediction of Contact Force in the Process of Shoveling Up Glass Subtrate [J]. Journal of South China University of Technology(Natural Science Edition), 2022, 50(8): 71-81.
[15]	MO Jianwen, ZHU Yanqiao, YUAN Hua, et al. Incremental learning based on neuron regularization and resource releasing [J]. Journal of South China University of Technology(Natural Science Edition), 2022, 50(6): 71-79,90.