Next Article in Journal
Analysis of Spatiotemporal Evolution and Driving Forces of Vegetation from 2001 to 2020: A Case Study of Shandong Province, China
Previous Article in Journal
A Comparative Literature Review of Machine Learning and Image Processing Techniques Used for Scaling and Grading of Wood Logs
 
 
Font Type:
Arial Georgia Verdana
Font Size:
Aa Aa Aa
Line Spacing:
Column Width:
Background:
This is an early access version, the complete PDF, HTML, and XML versions will be available soon.
Article

FireYOLO-Lite: Lightweight Forest Fire Detection Network with Wide-Field Multi-Scale Attention Mechanism

College of Information Engineering, Beijing Institute of Petrochemical Technology, Beijing 102617, China
*
Author to whom correspondence should be addressed.
Forests 2024, 15(7), 1244; https://doi.org/10.3390/f15071244 (registering DOI)
Submission received: 28 May 2024 / Revised: 12 July 2024 / Accepted: 15 July 2024 / Published: 17 July 2024
(This article belongs to the Section Natural Hazards and Risk Management)

Abstract

A lightweight forest fire detection model based on YOLOv8 is proposed in this paper in response to the problems existing in traditional sensors for forest fire detection. The performance of traditional sensors is easily constrained by hardware computing power, and their adaptability in different environments needs improvement. To balance the accuracy and speed of fire detection, the GhostNetV2 lightweight network is adopted to replace the backbone network for feature extraction of YOLOv8. The Ghost module is utilized to replace traditional convolution operations, conducting feature extraction independently in different dimensional channels, significantly reducing the complexity of the model while maintaining excellent performance. Additionally, an improved CPDCA channel priority attention mechanism is proposed, which extracts spatial features through dilated convolution, thereby reducing computational overhead and enabling the model to focus more on fire targets, achieving more accurate detection. In response to the problem of small targets in fire detection, the Inner IoU loss function is introduced. By adjusting the size of the auxiliary bounding boxes, this function effectively enhances the convergence effect of small target detection, further reducing missed detections, and improving overall detection accuracy. Experimental results indicate that, compared with traditional methods, the algorithm proposed in this paper significantly improves the average precision and FPS of fire detection while maintaining a smaller model size. Through experimental analysis, compared with YOLOv3-tiny, the average precision increased by 5.9% and the frame rate reached 285.3 FPS when the model size was only 4.9 M; compared with Shufflenet, the average precision increased by 2.9%, and the inference speed tripled. Additionally, the algorithm effectively addresses false positives, such as cloud and reflective light, further enhancing the detection of small targets and reducing missed detections.
Keywords: lightweight network; dilated convolutions; breadth spatial vision; small fire targets; CPDCA attention module; fire detection; YOLOv8; deep learning lightweight network; dilated convolutions; breadth spatial vision; small fire targets; CPDCA attention module; fire detection; YOLOv8; deep learning

Share and Cite

MDPI and ACS Style

Sheng, S.; Liang, Z.; Xu, W.; Wang, Y.; Su, J. FireYOLO-Lite: Lightweight Forest Fire Detection Network with Wide-Field Multi-Scale Attention Mechanism. Forests 2024, 15, 1244. https://doi.org/10.3390/f15071244

AMA Style

Sheng S, Liang Z, Xu W, Wang Y, Su J. FireYOLO-Lite: Lightweight Forest Fire Detection Network with Wide-Field Multi-Scale Attention Mechanism. Forests. 2024; 15(7):1244. https://doi.org/10.3390/f15071244

Chicago/Turabian Style

Sheng, Sha, Zhengyin Liang, Wenxing Xu, Yong Wang, and Jiangdan Su. 2024. "FireYOLO-Lite: Lightweight Forest Fire Detection Network with Wide-Field Multi-Scale Attention Mechanism" Forests 15, no. 7: 1244. https://doi.org/10.3390/f15071244

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Metrics

Article metric data becomes available approximately 24 hours after publication online.
Back to TopTop