A light weight multi-scale feature fusion steel surface defect detection model based on YOLOv8

被引:24
|
作者
Xie, Weining [1 ]
Sun, Xiaoyong [1 ]
Ma, Weifeng [1 ]
机构
[1] Zhejiang Univ Sci & Technol, Sch Informat & Elect Engn, 318 Liuhe Rd, Hangzhou 310023, Zhejiang, Peoples R China
关键词
defect detection; YOLOv8; deep learning; feature fusion;
D O I
10.1088/1361-6501/ad296d
中图分类号
T [工业技术];
学科分类号
08 ;
摘要
In industrial production, the steel surface may incur different defects owing to the influence of external factors, thereby affecting the performance of steel. With the increasing requirements for steel quality, achieving efficient detection of steel surface defects is a difficult problem that urgently needs to be solved. Traditional steel surface defect detection methods are limited by poor detection performance and slow detection speed. Therefore, a model named LMS-YOLO, based on YOLOv8, is proposed in this paper for achieving efficient steel surface defect detection. Firstly, in backbone, the light weight multi-scale mixed convolution (LMSMC) module is designed to fuse with C2f to obtain C2f_LMSMC, so as to extract the features of different scales for fusion and achieve the light weight of the network. Meanwhile, the proposed efficient global attention mechanism was added to backbone to enhance cross dimensional information interaction and feature extraction capabilities, and to achieve a more efficient attention mechanism. In neck, using channel tuning to achieve better cross scale fusion in BiFPN. Finally, the model uses three independent decoupled heads for regression and classification, and replaces CIoU with NWD as the regression loss to enhance the effect of detecting small scale defects. The experimental results showed that LMS-YOLO achieved 81.1 mAP and 61.3 FPS on NEU-DET, 80.5 mAP and 61.3 FPS on GC10-DET, respectively. The mAP increased by 2.8 and 4.7 compared to YOLOv8, and decreased by 17.4% in floating point operations (GFLOPs) and 34.2% in parameters (Params), which indicates that the model proposed in this paper has a better comprehensive performance compared with other methods in steel surface defect detection.
引用
收藏
页数:17
相关论文
共 50 条
  • [11] Optimized YOLOv8 for multi-scale object detection
    Rasheed, Areeg Fahad
    Zarkoosh, M.
    JOURNAL OF REAL-TIME IMAGE PROCESSING, 2025, 22 (01)
  • [12] An improved YOLOv8 model and mask convolutional autoencoder for multi-scale defect detection of ceramic tiles
    Liu, Yuesheng
    Qiu, Weibin
    Fu, Kailong
    Chen, Xindu
    Wu, Lei
    Sun, Mingyang
    MEASUREMENT, 2025, 248
  • [13] Improved YOLOv8 Method for Anomaly Behavior Detection with Multi-Scale Fusion and FMB
    Shi, Yangyu
    Zuo, Jing
    Xie, Chengjie
    Zheng, Diwen
    Lu, Shuhua
    Computer Engineering and Applications, 2024, 60 (09) : 101 - 110
  • [14] Steel surface defect detection based on MobileViTv2 and YOLOv8
    Lv, Zhongliang
    Zhao, Zhiqiang
    Xia, Kewen
    Gu, Guojun
    Liu, Kang
    Chen, Xuanlin
    JOURNAL OF SUPERCOMPUTING, 2024, 80 (13): : 18919 - 18941
  • [15] YOLO-GP: A Multi-Scale Dangerous Behavior Detection Model Based on YOLOv8
    Liu, Bushi
    Yu, Cuiying
    Chen, Bolun
    Zhao, Yue
    SYMMETRY-BASEL, 2024, 16 (06):
  • [16] Improved YOLOv8 Method for Multi-scale Pothole Detection
    Chang, Jiarui
    Chen, Zhan
    Xia, E.
    ADVANCED INTELLIGENT COMPUTING TECHNOLOGY AND APPLICATIONS, PT XI, ICIC 2024, 2024, 14872 : 383 - 395
  • [17] Insulator Defect Detection Based on Multi-Scale Feature Fusion
    Bin L.
    Luyao Q.
    Xinshan Z.
    Zhimin G.
    Yangyang T.
    Diangong Jishu Xuebao/Transactions of China Electrotechnical Society, 2023, 38 (01): : 60 - 70
  • [18] CRGF-YOLO: An Optimized Multi-Scale Feature Fusion Model Based on YOLOv5 for Detection of Steel Surface Defects
    Yu, Tao
    Luo, Xu
    Li, Qiang
    Li, Lei
    INTERNATIONAL JOURNAL OF COMPUTATIONAL INTELLIGENCE SYSTEMS, 2024, 17 (01)
  • [19] MDD-YOLOv8: A Multi-Scale Object Detection Model Based on YOLOv8 for Synthetic Aperture Radar Images
    Liu, Jie
    Liu, Xue
    Chen, Huaixin
    Luo, Sijie
    APPLIED SCIENCES-BASEL, 2025, 15 (04):
  • [20] Metal Surface Defect Detection Based on a Transformer with Multi-Scale Mask Feature Fusion
    Zhao, Lin
    Zheng, Yu
    Peng, Tao
    Zheng, Enrang
    SENSORS, 2023, 23 (23)