Lv Baozhan, Duan Beiyang, Zhang Yeming, Li Shuping, Wei Feng, Gong Sanpeng, Ma Qiji, Cai Maolin
School of Mechanical and Power Engineering, Henan Polytechnic University, Jiaozuo 454003, China.
School of Automation Science and Electrical Engineering, Beihang University, Beijing 100191, China.
Sensors (Basel). 2024 Apr 23;24(9):2667. doi: 10.3390/s24092667.
Surface defect detection of strip steel is an important guarantee for improving the production quality of strip steel. However, due to the diverse types, scales, and texture structures of surface defects on strip steel, as well as the irregular distribution of defects, it is difficult to achieve rapid and accurate detection of strip steel surface defects with existing methods. This article proposes a real-time and high-precision surface defect detection algorithm for strip steel based on YOLOv7. Firstly, Partial Conv is used to replace the conventional convolution blocks of the backbone network to reduce the size of the network model and improve the speed of detection; Secondly, The CA attention mechanism module is added to the ELAN module to enhance the ability of the network to extract detect features and improve the effectiveness of detect detection in complex environments; Finally, The SPD convolution module is introduced at the output end to improve the detection performance of small targets with surface defects on steel. The experimental results on the NEU-DET dataset indicate that the mean average accuracy (mAP@IoU = 0.5) is 80.4%, which is 4.0% higher than the baseline network. The number of parameters is reduced by 8.9%, and the computational load is reduced by 21.9% (GFLOPs). The detection speed reaches 90.9 FPS, which can well meet the requirements of real-time detection.
带钢表面缺陷检测是提高带钢生产质量的重要保障。然而，由于带钢表面缺陷的类型、尺度和纹理结构多样，且缺陷分布不规则，采用现有方法难以实现带钢表面缺陷的快速、准确检测。本文提出一种基于YOLOv7的带钢实时高精度表面缺陷检测算法。首先，使用Partial Conv替换主干网络的传统卷积块，以减小网络模型尺寸并提高检测速度；其次，在ELAN模块中添加CA注意力机制模块，增强网络提取检测特征的能力，提高复杂环境下检测的有效性；最后，在输出端引入SPD卷积模块，提高对带钢表面小目标缺陷的检测性能。在NEU-DET数据集上的实验结果表明，平均精度均值（mAP@IoU = 0.5）为80.4%，比基线网络高4.0%。参数数量减少8.9%，计算量减少21.9%（GFLOPs）。检测速度达到90.9 FPS，能够很好地满足实时检测要求。
