Surface defect detection algorithm for continuous casting billets based on improved YOLOv7
To address the challenges of low accuracy and slow detection speed in identifying surface defects of casting billets during continuous casting production,an enhanced surface defect detection algorithm based on improved YOLOv7-Tiny was presented.Firstly,adaptive and efficient layer aggregation network coupled with distributed shift convolution was introduced to augment the ability of feature information extraction at different scales,thereby enhancing model generalization and computational efficiency.Secondly,coordinated attention module was incorpo-rated into the feature fusion component to amplify the perception of channel and position information,thereby im-proving the capturing ability of crucial features and strengthening feature fusion.Simultaneously,the Minimum Point Distance IoU(MPDIoU)loss was introduced to overcome limitations in existing loss functions,which could boost the accuracy of regression results and expedite model convergence.Lastly,utilizing actual production images of continuous casting billets defects,a dataset was constructed and verified.Experimental results reveal that it has substantial improvements for improved YOLOv7 algorithm compared to the baseline network.The improved YOLOv7 algorithm achieves 35％reduction in computational complexity,4.4 percent point increase in accuracy,and 2.8 percent point increase in average precision(mAP)while maintaining the same number of parameters.With de-tection speed of 130 FPS,it meets real-time defect detection requirements at continuous casting production sites and demonstrates robust generalization on the NEU-DET public dataset.The defect detection algorithm proposed in this study offers technical support for enhancing the accuracy of defect detection and optimizing the inspection process.
surface defect of casting billetobject detectionYOLOv7-Tinyattention mechanismloss function
NETL
NSTL
万方数据
