A Lightweight Wildfire Detection Method for Transmission Line Perimeters

被引:3
|
作者
Huang, Xiaolong [1 ]
Xie, Weicheng [1 ]
Zhang, Qiwen [1 ]
Lan, Yeshen [1 ]
Heng, Huiling [1 ]
Xiong, Jiawei [1 ]
机构
[1] Xihua Univ, Sch Elect Engn & Elect Informat, Chengdu 610039, Peoples R China
关键词
transmission line; YOLOv8; wildfire; lightweight model;
D O I
10.3390/electronics13163170
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Due to extreme weather conditions and complex geographical features, the environments around power lines in forest areas have a high risk of wildfires. Once a wildfire occurs, it causes severe damage to the forest ecosystem. Monitoring wildfires around power lines in forested regions through deep learning can reduce the harm of wildfires to natural environments. To address the challenges of wildfire detection around power lines in forested areas, such as interference from complex environments, difficulty detecting small target objects, and high model complexity, a lightweight wildfire detection model based on the improved YOLOv8 is proposed. Firstly, we enhanced the image-feature-extraction capability using a novel feature-extraction network, GS-HGNetV2, and replaced the conventional convolutions with a Ghost Convolution (GhostConv) to reduce the model parameters. Secondly, the use of the RepViTBlock to replace the original Bottleneck in C2f enhanced the model's feature-fusion capability, thereby improving the recognition accuracy for small target objects. Lastly, we designed a Resource-friendly Convolutional Detection Head (RCD), which reduces the model complexity while maintaining accuracy by sharing the parameters. The model's performance was validated using a dataset of 11,280 images created by merging a custom dataset with the D-Fire data for monitoring wildfires near power lines. In comparison to YOLOv8, our model saw an improvement of 3.1% in the recall rate and 1.1% in the average precision. Simultaneously, the number of parameters and computational complexity decreased by 54.86% and 39.16%, respectively. The model is more appropriate for deployment on edge devices with limited computational power.
引用
收藏
页数:18
相关论文
共 50 条
  • [41] Assessing Accuracy of Manually-mapped Wildfire Perimeters in Topographically Dissected Areas
    Crystal A. Kolden
    Peter J. Weisberg
    Fire Ecology, 2007, 3 (1) : 22 - 31
  • [42] Mapped versus actual burned area within wildfire perimeters: Characterizing the unburned
    Kolden, Crystal A.
    Lutz, James A.
    Key, Carl H.
    Kane, Jonathan T.
    van Wagtendonk, Jan W.
    FOREST ECOLOGY AND MANAGEMENT, 2012, 286 : 38 - 47
  • [43] Detection Technology of Foamed Mixture Lightweight Soil Embankment Based on Ultrasonic Wave Transmission Method
    Pu, Shikun
    Hong, Baoning
    Liu, Xin
    Xu, Fenqiang
    Shan, Hao
    ADVANCES IN MATERIALS SCIENCE AND ENGINEERING, 2019, 2019
  • [44] Recursive Updates of Wildfire Perimeters Using Barrier Points and Ensemble Kalman Filtering
    Subramanian, Abhishek
    Tan, Li
    de Callafon, Raymond A.
    Crawl, Daniel
    Altintas, Ilkay
    COMPUTATIONAL SCIENCE - ICCS 2020, PT VI, 2020, 12142 : 225 - 236
  • [45] A lightweight hybrid detection method for botnet
    Ma W.
    Wang X.
    Wang J.
    Chen Q.
    International Journal of Circuits, Systems and Signal Processing, 2021, 15 : 960 - 969
  • [46] A Novel Lightweight Grape Detection Method
    Su, Shuzhi
    Chen, Runbin
    Fang, Xianjin
    Zhu, Yanmin
    Zhang, Tian
    Xu, Zengbao
    AGRICULTURE-BASEL, 2022, 12 (09):
  • [47] A lightweight fast object detection method
    Jia, Yan-Fei
    Chen, Guang-Da
    Jiang, Zi-Cong
    Yang, Miao
    Xing, Li-Yun
    Cui, Ying
    Journal of Network Intelligence, 2022, 7 (01): : 209 - 221
  • [48] Lightweight mixture faults detection method for gasoline engine using on-line trend analysis
    Wu, Shili
    Tang, Zhenmin
    Guo, Zhaosong
    INTERNATIONAL JOURNAL OF AUTOMOTIVE TECHNOLOGY, 2017, 18 (03) : 365 - 375
  • [49] Lightweight mixture faults detection method for gasoline engine using on-line trend analysis
    Shili Wu
    Zhenmin Tang
    Zhaosong Guo
    International Journal of Automotive Technology, 2017, 18 : 365 - 375
  • [50] TLI-YOLOv5: A Lightweight Object Detection Framework for Transmission Line Inspection by Unmanned Aerial Vehicle
    Huang, Hanqiang
    Lan, Guiwen
    Wei, Jia
    Zhong, Zhan
    Xu, Zirui
    Li, Dongbo
    Zou, Fengfan
    ELECTRONICS, 2023, 12 (15)