改进YOLOv5的轻量级带钢表面缺陷检测

针对工业场景下设备资源有限的情况,提出一种改进YOLOv5的轻量化带钢缺陷检测模型.首先,使用Shuffle Netv2代替主干特征提取网络,优化模型参数量和运行速度;其次,采用轻量级上采样算子CARAFE (contentaware reassembly of features),在增大感受野的同时进一步降低参数和计算量;同时引入GSConv层,在保证语义信息的同时平衡模型准确性与检测速度;最后,设计一种跨层级特征融合机制,提高网络的检测精度.实验结果表明,改进后的模型的平均检测精度为78.5%,相较于原始YOLOv5算法提升了1.4%;模型计算量为10.9 GFLOPs,参数量为5.88×10⁶,计算量和参数量分别降低31%和15.4%;检测速度为49 f/s,提升了3.5 f/s.因此,改进后的模型提高了检测精度和检测速度,并且大幅降低了模型的计算量和参数量,能够满足对带钢表面缺陷进行实时检测.

Lightweight Strip Steel Defect Detection Based on Improved YOLOv5

For limited equipment resources in industrial scenarios, a lightweight strip steel defect detection model based on improved YOLOv5 is proposed. First, ShuffleNetv2 is used to replace the backbone feature extraction network to optimize model parameter amount and running speed; secondly, the lightweight up-sampling operator, namely content-aware reassembly of features (CARAFE) is used to further reduce parameters and calculation amount while increasing the receptive field. At the same time, the GSConv layer is introduced to balance the model accuracy and detection speed while ensuring semantic information. Finally, a cross-level feature fusion mechanism is designed to improve the detection accuracy of the network. The experimental results show that the mean average precision of the improved model is 78.5%, which is 1.4% higher than the original YOLOv5 algorithm. The calculation amount of the model is 10.9 GFLOPs; the parameter amount is 5.88×10⁶; the calculation and parameter amounts are reduced by 31% and 15.4%, respectively; the detection speed is 49 f/s, which is increased by 3.5 f/s. Therefore, the improved model improves the detection accuracy and speed and greatly reduces the calculation and parameter amounts of the model, which can ensure the real-time detection of surface defects of strip steel.