An effective graph embedded YOLOv5 model for forest fire detection

被引:6
作者
Yuan, Hui [1 ]
Lu, Zhumao [1 ]
Zhang, Ruizhe [2 ]
Li, Jinsong [1 ,3 ]
Wang, Shuai [1 ]
Fan, Jingjing [1 ]
机构
[1] State Grid Shanxi Elect Power Res Inst, Taiyuan, Peoples R China
[2] State Grid Beijing Elect Power Res Inst, Beijing, Peoples R China
[3] State Grid Shanxi Elect Power Res Inst, Taiyuan 030001, Peoples R China
关键词
context information; forest fire detection; graph embedded operation; multi-head self-attention; YOLOv5;
D O I
10.1111/coin.12640
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
The existing YOLOv5-based framework has achieved great success in the field of target detection. However, in forest fire detection tasks, there are few high-quality forest fire images available, and the performance of the YOLO model has suffered a serious decline in detecting small-scale forest fires. Making full use of context information can effectively improve the performance of small target detection. To this end, this paper proposes a new graph-embedded YOLOv5 forest fire detection framework, which can improve the performance of small-scale forest fire detection using different scales of context information. To mine local context information, we design a spatial graph convolution operation based on the message passing neural network (MPNN) mechanism. To utilize global context information, we introduce a multi-head self-attention (MSA) module before each YOLO head. The experimental results on FLAME and our self-built fire dataset show that our proposed model improves the accuracy of small-scale forest fire detection. The proposed model achieves high performance in real-time performance by fully utilizing the advantages of the YOLOv5 framework.
引用
收藏
页数:17
相关论文
共 56 条
[31]  
Premal CE., Image processing based forest fire detection using YCbCr colour model. Paper presented at: International Conference on Circuit. IEEE
[32]  
2015. Wildfire smoke detection using convolutional neural networks
[33]  
Qi-xing Zhang, 2018, Procedia Engineering, V211, P441, DOI 10.1016/j.proeng.2017.12.034
[34]  
Rao RM., MSA transformer. Paper presented at: International Conference on Machine Learning. PMLR
[35]  
2021
[36]   You Only Look Once: Unified, Real-Time Object Detection [J].
Redmon, Joseph ;
Divvala, Santosh ;
Girshick, Ross ;
Farhadi, Ali .
2016 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2016, :779-788
[37]  
Shamsoshoara A., Aerial Imagery Pile Burn Detection Using Deep Learning: the FLAME Dataset
[38]  
2020
[39]  
Shao Z., 2023, Emergency Management Science and Technology, V3
[40]   Offline signature verification using deep neural network with application to computer vision [J].
Sharma, Neha ;
Gupta, Sheifali ;
Mehta, Puneet ;
Cheng, Xiaochun ;
Shankar, Achyut ;
Singh, Prabhishek ;
Nayak, Soumya Ranjan .
JOURNAL OF ELECTRONIC IMAGING, 2022, 31 (04)