A Lightweight Fire Detection Algorithm Based on the Improved YOLOv8 Model

被引:3
作者
Ma, Shuangbao [1 ,2 ]
Li, Wennan [2 ]
Wan, Li [3 ]
Zhang, Guoqin [4 ]
机构
[1] Wuhan Text Univ, Hubei Key Lab Digital Text Equipment, Wuhan 430200, Peoples R China
[2] Wuhan Text Univ, Sch Mech Engn & Automat, Wuhan 430200, Peoples R China
[3] Wuhan Text Univ, Sch Econ, Wuhan 430200, Peoples R China
[4] Wuhan Text Univ, Sch Elect & Elect Engn, Wuhan 430200, Peoples R China
来源
APPLIED SCIENCES-BASEL | 2024年 / 14卷 / 16期
基金
中国国家自然科学基金;
关键词
object detection; fire detection; lightweight; ghostnet; CARAFE;
D O I
10.3390/app14166878
中图分类号
O6 [化学];
学科分类号
0703 ;
摘要
Aiming at solving the issues that fire detection is prone to be affected by environmental factors, and the accuracy of flame and smoke detection remains relatively low at the incipient stage of fire, a fire detection algorithm based on GCM-YOLO is put forward. Firstly, GhostNet is introduced to optimize the backbone network, enabling the model to be lightweight without sacrificing model accuracy. Secondly, the upsampling module is reorganized with content-aware features to enhance the detail capture and information fusion effect of the model. Finally, by incorporating the mixed local channel attention mechanism in the neck, the model can enhance the processing capability of complex scenes. The experimental results reveal that, compared with the baseline model YOLOv8n, the GCM-YOLO model in fire detection increases the mAP@0.5 by 1.2%, and the number of parameters and model size decrease by 38.3% and 34.9%, respectively. The GCM-YOLO model can raise the accuracy of fire detection while reducing the computational burden and is suitable for deployment in practical application scenarios such as mobile terminals.
引用
收藏
页数:13
相关论文
共 21 条
  • [1] A Review on Forest Fire Detection Techniques
    Alkhatib, Ahmad A. A.
    [J]. INTERNATIONAL JOURNAL OF DISTRIBUTED SENSOR NETWORKS, 2014,
  • [2] Wildfire and Smoke Detection Using Staged YOLO Model and Ensemble CNN
    Bahhar, Chayma
    Ksibi, Amel
    Ayadi, Manel
    Jamjoom, Mona M. M.
    Ullah, Zahid
    Soufiene, Ben Othman
    Sakli, Hedi
    [J]. ELECTRONICS, 2023, 12 (01)
  • [3] A Review on Early Forest Fire Detection Systems Using Optical Remote Sensing
    Barmpoutis, Panagiotis
    Papaioannou, Periklis
    Dimitropoulos, Kosmas
    Grammalidis, Nikos
    [J]. SENSORS, 2020, 20 (22) : 1 - 26
  • [4] A Probabilistic Approach for Vision-Based Fire Detection in Videos
    Borges, Paulo Vinicius Koerich
    Izquierdo, Ebroul
    [J]. IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, 2010, 20 (05) : 721 - 731
  • [5] ERF-YOLO: A YOLO algorithm compatible with fewer parameters and higher accuracy
    Chai, Enhui
    Ta, Lin
    Ma, Zhanfei
    Zhi, Min
    [J]. IMAGE AND VISION COMPUTING, 2021, 116
  • [6] El-afifi M.I., 2024, Nile J. Commun. Comput. Sci, V7, P58, DOI [10.21608/njccs.2024.263103.1027, DOI 10.21608/NJCCS.2024.263103.1027]
  • [7] Double-Step U-Net: A Deep Learning-Based Approach for the Estimation of Wildfire Damage Severity through Sentinel-2 Satellite Data
    Farasin, Alessandro
    Colomba, Luca
    Garza, Paolo
    [J]. APPLIED SCIENCES-BASEL, 2020, 10 (12):
  • [8] How the science of injury prevention contributes to advancing home fire safety in the USA: successes and opportunities
    Gielen, Andrea C.
    Frattaroli, Shannon
    Pollack, Keshia M.
    Peek-Asa, Corinne
    Yang, Jingzhen G.
    [J]. INJURY PREVENTION, 2018, 24 : I7 - I13
  • [9] A lightweight YOLOv8 integrating FasterNet for real-time underwater object detection
    Guo, An
    Sun, Kaiqiong
    Zhang, Ziyi
    [J]. JOURNAL OF REAL-TIME IMAGE PROCESSING, 2024, 21 (02)
  • [10] Fire safety in modern indoor and built environment
    Ivanov, Martin Lyubomirov
    Chow, Wan-Ki
    [J]. INDOOR AND BUILT ENVIRONMENT, 2023, 32 (01) : 3 - 8