YOLOv5用于太阳电池缺陷检测优化研究

麦耀华; 吴绍航; 高彦艳; 李阳; 李玉娟; 周界龙

doi:10.19912/j.0254-0096.tynxb.2023-1027

PDF(2889 KB)

太阳能学报 ›› 2024, Vol. 45 ›› Issue (11) : 162-169. DOI: 10.19912/j.0254-0096.tynxb.2023-1027

YOLOv5用于太阳电池缺陷检测优化研究

李玉娟^1,2, 周界龙³, 麦耀华^2,4, 吴绍航^2,4, 高彦艳^2,4, 李阳¹

作者信息 +

YOLOv5 IS USED IN OPTIMIZATION OF SURFACE DEFECT DETECTION OF SOLAR CELLS

Li Yujuan^1,2, Zhou Jielong³, Mai Yaohua^2,4, Wu Shaohang^2,4, Gao Yanyan^2,4, Li Yang¹

Author information +

文章历史 +

摘要

在新能源应用技术中,太阳电池表面缺陷检测是至关重要的技术环节。该文研究并提出一种基于YOLOv5算法的优化模型,可对静态图片进行检测也可用于实时视频中。将坐标注意力机制（CA）加入到YOLOv5的主干网络部分。再将颈部网络部分的特征融合部分优化为BiFPN结构。最后,为解决正负样本数量失衡问题,开启Focal Loss,并将其优化为Varifocal Loss。将此优化算法应用在PVEL-AD数据集上,并将mAP@0.5作为验证标准。验证结果表明,该研究所使用算法的检测精度达到86.24%,相较于未优化的原始算法提升5.64%。

Abstract

In the field of new energy application technology, surface defect detection of solar cells is a crucial technical component. An optimized model based on the YOLOv5 algorithm is researched and proposed, which can detect static images and be used in real-time video. The model incorporates coordinate attention （CA） into the backbone network of YOLOv5 and optimizes the feature fusion part of the neck network using BiFPN structure. Furthermore, to address the issue of imbalanced positive and negative samples, Focal Loss is employed and optimized to Varifocal Loss. This optimized algorithm is applied to the PVEL-AD dataset, with mAP@0.5 used as the validation metric. The validation results demonstrate that the algorithm achieves a detection accuracy of 86.24%, which represents a 5.64% improvement compared to the unoptimized original algorithm.

导出引用

李玉娟, 周界龙, 麦耀华, 吴绍航, 高彦艳, 李阳. YOLOv5用于太阳电池缺陷检测优化研究[J]. 太阳能学报. 2024, 45(11): 162-169 https://doi.org/10.19912/j.0254-0096.tynxb.2023-1027

Li Yujuan, Zhou Jielong, Mai Yaohua, Wu Shaohang, Gao Yanyan, Li Yang. YOLOv5 IS USED IN OPTIMIZATION OF SURFACE DEFECT DETECTION OF SOLAR CELLS[J]. Acta Energiae Solaris Sinica. 2024, 45(11): 162-169 https://doi.org/10.19912/j.0254-0096.tynxb.2023-1027

中图分类号： TP391

参考文献

[1] GIRSHICK R, DONAHUE J, DARRELL T, et al.Rich feature hierarchies for accurate object detection and semantic segmentation[C]//2014 IEEE Conference on Computer Vision and Pattern Recognition. Columbus, OH, USA, 2014: 580-587.
[2] GIRSHICK R.Fast R-CNN[C]//2015 IEEE International Conference on Computer Vision (ICCV). Santiago, Chile, 2015: 1440-1448.
[3] REN S Q, HE K M, GIRSHICK R, et al.Faster R-CNN: towards real-time object detection with region proposal networks[J]. IEEE transactions on pattern analysis and machine intelligence, 2017, 39(6): 1137-1149.
[4] HE K M, ZHANG X Y, REN S 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.
[5] LIU W, ANGUELOV D, ERHAN D, et al.SSD: single shot MultiBox detector[M]//LEIBE B, MATAS J, SEBE N, et al, eds. Computer Vision-ECCV 2016. Cham: Springer International Publishing, 2016: 21-37.
[6] REDMON J, DIVVALA S, GIRSHICK R, et al.You only look once: unified, real-time object detection[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Las Vegas, NV, USA, 2016: 779-788.
[7] REDMON J, FARHADI A.YOLO9000: better, faster, stronger[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Honolulu, HI, USA, 2017: 6517-6525.
[8] REDMON J, FARHADI A.YOLOv3: an incremental improvement[J]. arXiv preprint arXiv:180402767, 2018.
[9] BOCHKOVSKIY A, WANG C Y, LIAO H Y M. YOLOv4: optimal speed and accuracy of object detection[EB/OL].2020: 2004.10934.http://arxiv.org/abs/2004.10934v1
[10] LIN T Y, GOYAL P, GIRSHICK R, et al.Focal loss for dense object detection[C]//2017 IEEE International Conference on Computer Vision (ICCV). Venice, Italy, 2017: 2999-3007.
[11] 陶志勇, 杜福廷, 任晓奎, 等. 基于T-VGG的太阳电池片缺陷检测[J]. 太阳能学报, 2022, 43(7): 145-151.
TAO Z Y, DU F T, REN X K, et al.Defect detection of solar cells based on T-VGG[J]. Acta energiae solaris sinica, 2022, 43(7): 145-151.
[12] 周颖, 叶红, 王彤, 等. 基于多尺度CNN的光伏组件缺陷识别[J]. 太阳能学报, 2022, 43(2): 211-216.
ZHOU Y, YE H, WANG T, et al.Photovoltaic module defect identification based on mulit-scale convolution neural network[J]. Acta energiae solaris sinica, 2022, 43(2): 211-216.
[13] 李琼, 吴文宝, 刘斌, 等. 基于迁移学习的光伏组件鸟粪覆盖检测[J]. 太阳能学报, 2022, 43(2): 233-237.
LI Q, WU W B, LIU B, et al.Bird droppings coverage detection of photovoltaic module based on transfer learning[J]. Acta energiae solaris sinica, 2022, 43(2): 233-237.
[14] CHEN A D, LI X, JING H Y, et al.Anomaly detection algorithm for photovoltaic cells based on lightweight multi-channel spatial attention mechanism[J]. Energies, 2023, 16(4): 1619.
[15] WOO S, PARK J, LEE J Y, et al.CBAM: convolutional block attention module[M]//Computer Vision-ECCV 2018. Cham: Springer International Publishing, 2018: 3-19.
[16] HARTIGAN J A, WONG M A.Algorithm AS 136: a K-means clustering algorithm[J]. Applied statistics, 1979, 28(1): 100.
[17] ZHENG Z H, WANG P, LIU W, et al.Distance-IoU loss: faster and better learning for bounding box regression[J]. Proceedings of the AAAI conference on artificial intelligence, 2020, 34(7): 12993-13000.
[18] ZEILER M D, FERGUS R.Visualizing and understanding convolutional networks[M]//Computer Vision-ECCV 2014. Cham: Springer International Publishing, 2014: 818-833.
[19] LIN T Y, DOLLÁR P, GIRSHICK R, et al. Feature pyramid networks for object detection[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Honolulu, HI, USA, 2017: 936-944.
[20] LI H C, XIONG P F, AN J, et al. Pyramid attention network for semantic segmentation[EB/OL].2018: 1805.10180.http://arxiv.org/abs/1805.10180v3
[21] TAN M X, PANG R M, LE Q V.EfficientDet: scalable and efficient object detection[C]//2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Seattle, WA, USA, 2020: 10778-10787.
[22] ZHANG H Y, WANG Y, DAYOUB F, et al.VarifocalNet: an IoU-aware dense object detector[C]//2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Nashville, TN, USA, 2021: 8510-8519.
[23] HOU Q B, ZHOU D Q, FENG J S.Coordinate attention for efficient mobile network design[C]//2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Nashville, TN, USA, 2021: 13708-13717.
[24] HU J, SHEN L, SUN G.Squeeze-and-excitation networks[C]//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City, UT, USA, 2018: 7132-7141.
[25] SU B Y, ZHOU Z, CHEN H Y.PVEL-AD: a large-scale open-world dataset for photovoltaic cell anomaly detection[J]. IEEE transactions on industrial informatics, 2023, 19(1): 404-413.