{"title":"钢板表面缺陷实时检测算法:starnet - gsconvr - ret3检测变压器(SSR-DETR)。","authors":"Zhuguo Zhou,Yujun Lu,Liye Lv","doi":"10.1111/nyas.15332","DOIUrl":null,"url":null,"abstract":"In view of the problems in industrial steel plate surface defect detection, such as high model complexity, insufficient recognition of small targets, and inefficient hardware deployment, this study proposes the StarNet-GSConv-RetC3 detection transformer (SSR-DETR) lightweight framework. The framework comprises a StarNet backbone network and an innovative star operation optimization structure to reduce computational complexity while enhancing feature representation capabilities. In the feature fusion stage, the RetBlock CSP bottleneck with 3 convolutions (RetC3) module with an explicit attenuation mechanism is designed to enhance the extraction of geometric features of microscopic defects by combining two-dimensional spatial priors, and grouped spatial convolution (GSConv) is used to optimize the aggregation of multiscale features. Experiments show that the algorithm achieves a mean average precision (mAP) of 88.2% and a classification accuracy of 92.0% on the Northeastern University steel surface defect (NEU-DET) dataset, which is 4.8% and 3.7% higher than the baseline model, respectively. Meanwhile, the model's computational load and size are reduced by 59.5% and 47.8%, respectively. Actual deployment tests show that this algorithm operates at 98.1 frames per second (FPS) on personal computer platforms and at 40.3 FPS, with a single-frame processing time of 24.8 ms, on the RK3568 embedded system, fully meeting the comprehensive requirements of industrial scenarios.","PeriodicalId":8250,"journal":{"name":"Annals of the New York Academy of Sciences","volume":"255 1","pages":""},"PeriodicalIF":4.1000,"publicationDate":"2025-05-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"A real-time defect detection algorithm for steel plate surfaces: the StarNet-GSConv-RetC3 detection transformer (SSR-DETR).\",\"authors\":\"Zhuguo Zhou,Yujun Lu,Liye Lv\",\"doi\":\"10.1111/nyas.15332\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"In view of the problems in industrial steel plate surface defect detection, such as high model complexity, insufficient recognition of small targets, and inefficient hardware deployment, this study proposes the StarNet-GSConv-RetC3 detection transformer (SSR-DETR) lightweight framework. The framework comprises a StarNet backbone network and an innovative star operation optimization structure to reduce computational complexity while enhancing feature representation capabilities. In the feature fusion stage, the RetBlock CSP bottleneck with 3 convolutions (RetC3) module with an explicit attenuation mechanism is designed to enhance the extraction of geometric features of microscopic defects by combining two-dimensional spatial priors, and grouped spatial convolution (GSConv) is used to optimize the aggregation of multiscale features. Experiments show that the algorithm achieves a mean average precision (mAP) of 88.2% and a classification accuracy of 92.0% on the Northeastern University steel surface defect (NEU-DET) dataset, which is 4.8% and 3.7% higher than the baseline model, respectively. Meanwhile, the model's computational load and size are reduced by 59.5% and 47.8%, respectively. Actual deployment tests show that this algorithm operates at 98.1 frames per second (FPS) on personal computer platforms and at 40.3 FPS, with a single-frame processing time of 24.8 ms, on the RK3568 embedded system, fully meeting the comprehensive requirements of industrial scenarios.\",\"PeriodicalId\":8250,\"journal\":{\"name\":\"Annals of the New York Academy of Sciences\",\"volume\":\"255 1\",\"pages\":\"\"},\"PeriodicalIF\":4.1000,\"publicationDate\":\"2025-05-13\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Annals of the New York Academy of Sciences\",\"FirstCategoryId\":\"103\",\"ListUrlMain\":\"https://doi.org/10.1111/nyas.15332\",\"RegionNum\":3,\"RegionCategory\":\"综合性期刊\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"MULTIDISCIPLINARY SCIENCES\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Annals of the New York Academy of Sciences","FirstCategoryId":"103","ListUrlMain":"https://doi.org/10.1111/nyas.15332","RegionNum":3,"RegionCategory":"综合性期刊","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"MULTIDISCIPLINARY SCIENCES","Score":null,"Total":0}
A real-time defect detection algorithm for steel plate surfaces: the StarNet-GSConv-RetC3 detection transformer (SSR-DETR).
In view of the problems in industrial steel plate surface defect detection, such as high model complexity, insufficient recognition of small targets, and inefficient hardware deployment, this study proposes the StarNet-GSConv-RetC3 detection transformer (SSR-DETR) lightweight framework. The framework comprises a StarNet backbone network and an innovative star operation optimization structure to reduce computational complexity while enhancing feature representation capabilities. In the feature fusion stage, the RetBlock CSP bottleneck with 3 convolutions (RetC3) module with an explicit attenuation mechanism is designed to enhance the extraction of geometric features of microscopic defects by combining two-dimensional spatial priors, and grouped spatial convolution (GSConv) is used to optimize the aggregation of multiscale features. Experiments show that the algorithm achieves a mean average precision (mAP) of 88.2% and a classification accuracy of 92.0% on the Northeastern University steel surface defect (NEU-DET) dataset, which is 4.8% and 3.7% higher than the baseline model, respectively. Meanwhile, the model's computational load and size are reduced by 59.5% and 47.8%, respectively. Actual deployment tests show that this algorithm operates at 98.1 frames per second (FPS) on personal computer platforms and at 40.3 FPS, with a single-frame processing time of 24.8 ms, on the RK3568 embedded system, fully meeting the comprehensive requirements of industrial scenarios.
期刊介绍:
Published on behalf of the New York Academy of Sciences, Annals of the New York Academy of Sciences provides multidisciplinary perspectives on research of current scientific interest with far-reaching implications for the wider scientific community and society at large. Each special issue assembles the best thinking of key contributors to a field of investigation at a time when emerging developments offer the promise of new insight. Individually themed, Annals special issues stimulate new ways to think about science by providing a neutral forum for discourse—within and across many institutions and fields.