IMPROVED YOLOV5-BASED DEEP LEARNING METHOD FOR DETECTINGHOT SPOT EFFECTIN PHTOTVOLTAIC MODULES

被引：0
|
作者：
Wang, Daolei [1 ]
Xiao, Beicheng [1 ]
Yao, Congrong [1 ]
Zhao, Wenbin [1 ]
Zhu, Rui [1 ]
机构：
[1] College of Computer Science and Technology, Shanghai University of Electric Power, Shanghai,201306, China
来源：
Taiyangneng Xuebao/Acta Energiae Solaris Sinica | 2024年 / 45卷 / 08期
关键词：
Aiming at the thermal spot detection of photovoltaic modules; an improved YOLOv5 based thermal spot detection algorithm was proposed. In this algorithm; Dilated block composed of cavity convolution is introduced to replace the original SPP block; which effectively reduces the heat spot information loss caused by pooling operation and improves the receptive field of the network. At the same time; the channel attention mechanism is added to the multi-scale detection process; which enhances the importance of the target region of hot spots and improves the detection performance of hot spots. A Lightweight block module composed of deep separable convolution is proposed; which effectively reduces the number of model parameters and improves the detection speed. The experimental results show that the improved YOLOv5 network can achieve fast and accurate detection of hot spots. Compared with the original algorithm; the AP of this method is increased by 1.5% to 98.65%; and the detection speed is increased by 25% to 31 fps. © 2024 Science Press. All rights reserved;
D O I：
10.19912/j.0254-0096.tynxb.2023-0563
中图分类号：
学科分类号：
摘要：
引用
收藏
页码：342 / 348
相关论文
共 50 条
  • [21] Improved YOLOv5-based pore defect detection algorithm for wire arc additive manufacturing
    Zhou, Xiangman
    Zheng, Shicheng
    Li, Runsheng
    Xiong, Xiaochen
    Yuan, Youlu
    Bai, Xingwang
    Fu, Junjian
    Zhang, Haiou
    MATERIALS TODAY COMMUNICATIONS, 2024, 39
  • [22] Research on Improved YOLOv5-based Military Target Recognition Algorithm Used in Complex Battlefield Environment
    Song X.
    Liu K.
    Gao S.
    Chen C.
    Yan K.
    Binggong Xuebao/Acta Armamentarii, 2024, 45 (03): : 934 - 947
  • [23] YOLOv5-Based Seabed Sediment Recognition Method for Side-Scan Sonar Imagery
    Wang, Ziwei
    Hu, Yi
    Ding, Jianxiang
    Shi, Peng
    JOURNAL OF OCEAN UNIVERSITY OF CHINA, 2023, 22 (06) : 1529 - 1540
  • [24] YOLOv5-Based Seabed Sediment Recognition Method for Side-Scan Sonar Imagery
    WANG Ziwei
    HU Yi
    DING Jianxiang
    SHI Peng
    JournalofOceanUniversityofChina, 2023, 22 (06) : 1529 - 1540
  • [25] Improved YOLOv5-Based Lightweight Object Detection Algorithm for People with Visual Impairment to Detect Buses
    Arifando, Rio
    Eto, Shinji
    Wada, Chikamune
    APPLIED SCIENCES-BASEL, 2023, 13 (09):
  • [26] YOLOv5-Based Seabed Sediment Recognition Method for Side-Scan Sonar Imagery
    Ziwei Wang
    Yi Hu
    Jianxiang Ding
    Peng Shi
    Journal of Ocean University of China, 2023, 22 : 1529 - 1540
  • [27] Improved Detection and Tracking of Objects Based on a Modified Deep Learning Model (YOLOv5)
    Nife N.I.
    Chtourou M.
    International Journal of Interactive Mobile Technologies, 2023, 17 (21): : 145 - 160
  • [28] Improved YOLOv5-Based Real-Time Road Pavement Damage Detection in Road Infrastructure Management
    Sami, Abdullah As
    Sakib, Saadman
    Deb, Kaushik
    Sarker, Iqbal H.
    ALGORITHMS, 2023, 16 (09)
  • [29] A Dynamic Obstacle Avoidance Method in Robotic Navigation Control Through YOLOv5-Based Object Detection
    Liu, Hechao
    Liu, Wei
    Alblehai, Fahad
    JOURNAL OF CIRCUITS SYSTEMS AND COMPUTERS, 2024, 33 (15)
  • [30] Fish detection method based on improved YOLOv5
    Li, Lei
    Shi, Guosheng
    Jiang, Tao
    AQUACULTURE INTERNATIONAL, 2023, 31 (05) : 2513 - 2530
12345