Steel surface defect detection based on lightweight YOLOv7

Abstract

Aiming at the problems of low detection efficiency and difficult positioning of traditional steel surface defect detection methods, a lightweight steel surface defect detection model based on you only look once version 7 (YOLOv7) is proposed. First, a cascading style sheets (CSS) block module is proposed, which uses more lightweight operations to obtain redundant information in the feature map, reduces the amount of computation, and effectively improves the detection speed. Secondly, the improved spatial pyramid pooling with cross stage partial convolutions (SPPCSPC) structure is adopted to ensure that the model can also pay attention to the defect location information while predicting the defect category information, obtain richer defect features. In addition, the convolution operation in the original model is simplified, which significantly reduces the size of the model and helps to improve the detection speed. Finally, using efficient intersection over union (EIOU) loss to focus on high-quality anchors, speed up convergence and improve positioning accuracy. Experiments were carried out on the Northeastern University-defect (NEU-DET) steel surface defect dataset. Compared with the original YOLOv7 model, the number of parameters of this model was reduced by 40%, the frames per second (FPS) reached 112, and the average accuracy reached 79.1%, the detection accuracy and speed have been improved, which can meet the needs of steel surface defect detection.

References

[1] QiaoY, WangG. Recent status of production, administration policies, and low-carbon technology development of China’s steel industry[J]. Metals, 2024, 14(4): 480-495

[2] LiJ, LiH, HuX, et al.. Research progress of surface defect detection technology based on deep learning[J]. Computer integrated manufacturing system, 2024, 30(3): 774-791

[3] TangX, ZhouJ, JianG, et al.. Nondestructive differential eddy current testing for corrosion detection on coated aluminium alloys[J]. Anti-corrosion methods and materials, 2024, 71(6): 855-867

[4] ZhaoB T, ChenY R, JiaX F, et al.. Steel surface defect detection algorithm in complex background scenarios[J]. Measurement, 2024, 237: 175-189

[5] GirshickR, DonahueJ, DarrellT, et al.. Rich feature hierarchies for accurate object detection and semantic segmentation[C]. 2014 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 23–28, 2014, Columbus, OH, USA, 2014, New York, IEEE: 580-587

[6] GirshickR. Fast R-CNN[C]. 2015 IEEE International Conference on Computer Vision (ICCV), December 7–13, 2015, Santiago, Chile, 2015, New York, IEEE: 1440-1448

[7] LinT Y, DollarP, GirshickR, et al.. Feature pyramid networks for object detection[C]. 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), July 21–26, 2017, Honolulu, HI, USA, 2017, New York, IEEE: 936-944

[8] LiuW, AngueloyD, ErhanD, et al.. SSD: single shot MultiBox detector[C]//European Conference on Computer Vision (ECCV), October 11–14, 2016, Amsterdam, The Netherlands. Heidelberg: Springer, 2016, 9905: 21-37

[9] LinT Y, GoyalP, GirshickR, et al.. Focal loss for dense object detection[C]. 2017 IEEE International Conference on Computer Vision (ICCV), October 22–29, 2017, Venice, Italy, 2017, New York, IEEE: 2999-3007

[10] RedmonJ, DivvalaS, GirshickR, et al.. You only look once: unified, real-time object detection[C]. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 27–30, 2016, Las Vegas, NV, USA, 2016, New York, IEEE: 779-788

[11] XingJ FSurface defect identification and system development of hot-rolled strip based on convolutional neural network[D], 2017, Shenyang, Northeastern University: 1-54(in Chinese)

[12] HeY, SongK C, MengQ G, et al.. An end-to-end steel surface defect detection approach via fusing multiple hierarchical features[J]. IEEE transactions on instrumentation and measurement, 2020, 69(4P2): 1493-1504

[13] XuQ, ZhuH J, FanH H, et al.. Research on improved YOLOv3 network on surface defect detection of steel plates[J]. Computer engineering and applications, 2020, 56(16): 265-272

[14] LianJ W, HeJ H, NiuY, et al.. Fast and accurate detection of surface defect based on improved YOLOv4[J]. Assembly automation, 2022, 42(1): 134-146

[15] WangC Y, BochkovskiyA, LiaoH Y M. YOLOv7: trainable bag-of-freebies sets new state-of-the-art for real-time object detectors[C]. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), June 17–24, 2023, Vancouver, Canada, 2023, New York, IEEE: 7464-7475

[16] WangC Y, LiaoH, WuY H, et al.. CSPNet: a new backbone that can enhance learning capability of CNN[C]. 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), June 13–19, 2020, Seattle, WA, USA, 2020, New York, IEEE: 1571-1580

[17] HeK M, ZhangX Y, RenS Q, et al.. Spatial pyramid pooling in deep convolutional networks for visual recognition[J]. IEEE transactions on pattern analysis and machine intelligence, 2015, 37(9): 1904-1916

[18] DingX, ZhangX, MaN, et al.. RepVGG: making VGG-style ConvNets great again[C]. 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), June 20–25, 2021, Nashville, TN, USA, 2021, New York, IEEE: 13733-13742

[19] HanK, WangY H, TianQ, et al.. GhostNet: more features from cheap operations[C]. IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), June 13–19, 2020, Seattle, WA, USA, 2020, New York, IEEE: 1577-1586

[20] WooS, ParkJ, LeeJ Y, et al.. CBAM: convolutional block attention module[C]. European Conference on Computer Vision (ECCV), September 8–14, 2018, Munich, Germany, 2018, Heidelberg, Springer: 3-19

[21] DuS, ZhangB, ZhangP, et al.. An improved bounding box regression loss function based on CIOU loss for multi-scale object detection[C]. 2021 IEEE 2nd International Conference on Pattern Recognition and Machine Learning (PRML), July 16–18, 2021, Chengdu, China, 2021, New York, IEEE: 92-98

[22] ZhangY F, RenW Q, ZhangZ, et al.. Focal and efficient IOU loss for accurate bounding box regression[J]. Neurocomputing, 2022, 506: 146-157

[23] ChenC Q, FanY C, WangL. Logo detection based on improved mosaic data enhancement and feature fusion[J]. Computer measurement and control, 2022, 30(10): 188-194

[24] YunS, HanD, OhS J, et al.. CutMix: regularization strategy to train strong classifiers with localizable features[C]. International Conference on Computer Vision, October 20–26, 2019, Seoul, Korea (South), 2019, New York, IEEE: 659-666

RIGHTS & PERMISSIONS

Tianjin University of Technology