Real-Time Steel Surface Defect Detection with Improved Multi-Scale YOLO-v5

Steel surface defect detection is an important issue when producing high-quality steel materials. Traditional defect detection methods are time-consuming and uneconomical and require manually designed prior information or extra supervisors. Surface defects have different representations and features at different scales, which make it challenging to automatically detect the locations and defect types. This paper proposes a real-time steel surface defect detection technology based on the YOLO-v5 detection network. In order to effectively explore the multi-scale information of the surface defect, a multi-scale explore block is especially developed in the detection network to improve the detection performance. Furthermore, the spatial attention mechanism is also developed to focus more on the defect information. Experimental results show that the proposed network can accurately detect steel surface defects with approximately 72% mAP and satisfies the real-time speed requirement.

Automated summary

Steel surface defect detection is crucial for producing high-quality materials. Traditional methods are time-consuming and uneconomical, requiring manual design or additional supervision. This paper proposes a real-time detection technology based on YOLO-v5 network, effectively exploring multi-scale information with a special block and focusing on defect information with a spatial attention mechanism. Experimental results show an approximately 72% mAP and real-time performance.