A Weak Fire Detection Method Based on YOLOv5 and PCA

被引:0
作者
Lyu, Liangwei [1 ]
Cao, Yuping [1 ]
Deng, Xiaogang [1 ]
Wang, Ping [1 ]
机构
[1] China Univ Petr East China, Coll Control Sci & Engn, Qingdao, Peoples R China
来源
2024 14TH ASIAN CONTROL CONFERENCE, ASCC 2024 | 2024年
关键词
image processing; object detection; fire detection; you only look once; principal component analysis; color feature; VIDEO; COLOR;
D O I
暂无
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
For the version 5 of you only look once (YOLOv5) based fire detection method, the confidence scores of weak fire regions are usually low, which can affect the fire detection rate. For the above problem, a novel weak fire detection method based on the YOLOv5 network and principal component analysis (YOLOv5-PCA) is proposed. Firstly, the YOLOv5 network is used to process real-time monitoring images and produce potential fire regions with confidence scores. If the confidence score of a potential region is medium, the principal component analysis is further applied to fuse the pixel color features of the potential region. A pixel monitoring statistic is built to detect weak fire pixels. In a potential region, if the proportion of fire pixels exceeds 1/3, it is considered that there is fire, and a fire alarm is activated. Simulation studies on 5049 images from 25 fire videos and 424 images from 2 non-fire videos are used to verify the effectiveness of the proposed method. Compared with the YOLOv5 based method, the proposed YOLOv5-PCA method can effectively increase fire detection rate by 49.06%, and correct many misidentified non-fire regions.
引用
收藏
页码:59 / 64
页数:6
相关论文
共 50 条
  • [31] Research on traffic light target detection method based on improved YOLOv5 algorithm
    Li, Shixin
    Wang, Kun
    Chen, Fankai
    Meng, Yue
    [J]. PROCEEDINGS OF 2023 7TH INTERNATIONAL CONFERENCE ON ELECTRONIC INFORMATION TECHNOLOGY AND COMPUTER ENGINEERING, EITCE 2023, 2023, : 351 - 356
  • [32] Evaluating YOLOv4 and YOLOv5 for Enhanced Object Detection in UAV-Based Surveillance
    Alhassan, Mugtaba Abdalrazig Mohamed
    Yilmaz, Ersen
    [J]. PROCESSES, 2025, 13 (01)
  • [33] Research on improved algorithm for helmet detection based on YOLOv5
    Shan, Chun
    Liu, Hongming
    Yu, Yu
    [J]. SCIENTIFIC REPORTS, 2023, 13 (01)
  • [34] An Improved Waste Detection and Classification Model Based on YOLOV5
    Hu, Fan
    Qian, Pengjiang
    Jiang, Yizhang
    Yao, Jian
    [J]. INTELLIGENT COMPUTING METHODOLOGIES, PT III, 2022, 13395 : 741 - 754
  • [35] Detection of River Floating Garbage Based on Improved YOLOv5
    Yang, Xingshuai
    Zhao, Jingyi
    Zhao, Li
    Zhang, Haiyang
    Li, Li
    Ji, Zhanlin
    Ganchev, Ivan
    [J]. MATHEMATICS, 2022, 10 (22)
  • [36] Lightweight Foggy Weather Detection Algorithm Based on YOLOv5
    Hou, Wenshuai
    Cui, Kaige
    Yan, Jun
    Chang, Jiaxiu
    [J]. 2024 4TH INTERNATIONAL CONFERENCE ON MACHINE LEARNING AND INTELLIGENT SYSTEMS ENGINEERING, MLISE 2024, 2024, : 338 - 341
  • [37] Lightweight highland barley detection based on improved YOLOv5
    Cai, Minghui
    Deng, Hui
    Cai, Jianwei
    Guo, Weipeng
    Hu, Zhipeng
    Yu, Dongzheng
    Zhang, Houxi
    [J]. PLANT METHODS, 2025, 21 (01)
  • [38] Infrared ship target detection algorithm based on YOLOv5
    Liu F.
    Sun J.
    Zhang S.
    Sang H.
    Sun X.
    [J]. Hongwai yu Jiguang Gongcheng/Infrared and Laser Engineering, 2023, 52 (10):
  • [39] Night Lighting Fault Detection Based on Improved YOLOv5
    Zhang, Feng
    Dai, Congqi
    Zhang, Wanlu
    Liu, Shu
    Guo, Ruiqian
    [J]. BUILDINGS, 2024, 14 (10)
  • [40] A Lightweight Model Based on YOLOv5 for Helmet Wearing Detection
    Zou, Xiongxin
    Chen, Zuguo
    Zhou, Yimin
    [J]. 4TH INTERNATIONAL CONFERENCE ON INFORMATICS ENGINEERING AND INFORMATION SCIENCE (ICIEIS2021), 2022, 12161