Mcan-YOLO: An Improved Forest Fire and Smoke Detection Model Based on YOLOv7

被引:1
|
作者
Liu, Hongying [1 ]
Zhu, Jun [2 ]
Xu, Yiqing [2 ]
Xie, Ling [1 ]
机构
[1] Nanjing Univ Sci & Technol, Zijin Coll, Sch Comp & Artificial Intelligence, Nanjing 210023, Peoples R China
[2] Nanjing Vocat Univ Ind Technol, Sch Comp & Software, Nanjing 210023, Peoples R China
来源
FORESTS | 2024年 / 15卷 / 10期
关键词
forest fire smoke detection; YOLOv7; normalization-based attention module; CARAFE; AFPN;
D O I
10.3390/f15101781
中图分类号
S7 [林业];
学科分类号
0829 ; 0907 ;
摘要
Forest fires pose a significant threat to forest resources and wildlife. To balance accuracy and parameter efficiency in forest fire detection, this study proposes an improved model, Mcan-YOLO, based on YOLOv7. In the Neck section, the asymptotic feature pyramid network (AFPN) was employed to effectively capture multi-scale information, replacing the traditional module. Additionally, the content-aware reassembly of features (CARAFE) replaced the conventional upsampling method, further reducing the number of parameters. The normalization-based attention module (NAM) was integrated after the ELAN-T module to enhance the recognition of various fire smoke features, and the Mish activation function was used to optimize model convergence. A real fire smoke dataset was constructed using the mean structural similarity (MSSIM) algorithm for model training and validation. The experimental results showed that, compared to YOLOv7-tiny, Mcan-YOLO improved precision by 4.6%, recall by 6.5%, and mAP50 by 4.7%, while reducing the number of parameters by 5%. Compared with other mainstream algorithms, Mcan-YOLO achieved better precision with fewer parameters.
引用
收藏
页数:22
相关论文
共 50 条
  • [1] Fs-yolo: fire-smoke detection based on improved YOLOv7
    Wang, Dongmei
    Qian, Ying
    Lu, Jingyi
    Wang, Peng
    Hu, Zhongrui
    Chai, Yongkang
    MULTIMEDIA SYSTEMS, 2024, 30 (04)
  • [2] FOREST FIRE DETECTION BASED ON IMPROVED YOLOV7 MODELING
    Yang, Q.
    Zhang, T.
    Tong, X.
    Hu, L. H.
    APPLIED ECOLOGY AND ENVIRONMENTAL RESEARCH, 2024, 22 (04): : 3123 - 3136
  • [3] RepVGG-YOLOv7: A Modified YOLOv7 for Fire Smoke Detection
    Chen, Xin
    Xue, Yipeng
    Hou, Qingshan
    Fu, Yan
    Zhu, Yaolin
    FIRE-SWITZERLAND, 2023, 6 (10):
  • [4] LMDFS: A Lightweight Model for Detecting Forest Fire Smoke in UAV Images Based on YOLOv7
    Chen, Gong
    Cheng, Renxi
    Lin, Xufeng
    Jiao, Wanguo
    Bai, Di
    Lin, Haifeng
    REMOTE SENSING, 2023, 15 (15)
  • [5] An Improved Forest Fire and Smoke Detection Model Based on YOLOv5
    Li, Junhui
    Xu, Renjie
    Liu, Yunfei
    FORESTS, 2023, 14 (04):
  • [6] Smoke and Fire Detection Based on YOLOv7 With Convolutional Structure Reparameterization and Lightweighting
    Hu, Junjie
    He, Yun
    Zeng, Ming
    Qian, Yingjing
    Zhang, Renmin
    IEEE SENSORS LETTERS, 2024, 8 (08) : 1 - 4
  • [7] EC-YOLO: Improved YOLOv7 Model for PCB Electronic Component Detection
    Luo, Shiyi
    Wan, Fang
    Lei, Guangbo
    Xu, Li
    Ye, Zhiwei
    Liu, Wei
    Zhou, Wen
    Xu, Chengzhi
    SENSORS, 2024, 24 (13)
  • [8] EP-YOLO: A Pipeline Leak Detection Algorithm Based on Improved YOLOv7
    Zhang, Jiali
    Lan, Xiaowen
    Wang, Shaofeng
    Liu, Wenjing
    IEEE ACCESS, 2024, 12 : 198132 - 198141
  • [9] Automatic Acne Detection Model Based on Improved YOLOv7
    Zhang, Delong
    Jin, Chunyang
    Zhang, Zhidong
    Cao, Xiyuan
    Xue, Chenyang
    IEEE ACCESS, 2024, 12 : 194390 - 194398
  • [10] Efficient forest fire detection based on an improved YOLO model
    Lei Cao
    Zirui Shen
    Sheng Xu
    Visual Intelligence, 2 (1):