首页|DLF-YOLOF:an improved YOLOF-based surface defect detection for steel plate

DLF-YOLOF:an improved YOLOF-based surface defect detection for steel plate

扫码查看
原文链接
  • NETL
  • NSTL
  • 万方数据
Surface defects can affect the quality of steel plate.Many methods based on computer vision are currently applied to surface defect detection of steel plate.However,their real-time performance and object detection of small defect are still unsatisfactory.An improved object detection network based on You Only Look One-level Feature(YOLOF)is proposed to show excellent performance in surface defect detection of steel plate,called DLF-YOLOF.First,the anchor-free detector is used to reduce the network hyperparameters.Secondly,deformable convolution network and local spatial attention module are introduced into the feature extraction network to increase the contextual information in the feature maps.Also,the soft non-maximum suppression is used to improve detection accuracy significantly.Finally,data augmentation is performed for small defect objects during training to improve detection accuracy.Experiments show the average precision and average precision for small objects are 42.7％and 33.5％at a detection speed of 62 frames per second on a single GPU,respectively.This shows that DLF-YOLOF has excellent performance to meet the needs of industrial real-time detection.

Steel surface defects detectionYOLOFAnchor-free detectorSmall object detectionReal-time detection

Guang-hu Liu、Mao-xiang Chu、Rong-fen Gong、Ze-hao Zheng

展开 >

School of Electronic and Information Engineering,University of Science and Technology Liaoning,Anshan 114051,Liaoning,China

Natural Science Foundation of Liaoning ProvinceBasic Scientific Research Project of Education Department of Liaoning ProvinceBasic Scientific Research Project of Education Department of Liaoning Province

2022-MS-3532020LNZD06LJKMZ20220640

2024

10.1007/s42243-023-01059-4

钢铁研究学报(英文版)
钢铁研究总院

钢铁研究学报(英文版)

CSTPCD
影响因子：0.584
ISSN：1006-706X
年,卷(期)：2024.31(2)
  • 32