基于改进YOLOv7-tiny的光伏电池缺陷检测算法

doi:10.3778/j.issn.1002-8331.2312-0089

摘要/Abstract

摘要： 针对光伏电池对于太阳能转化效率不稳定的问题，提高光伏电池的质量，提出基于改进YOLOv7-tiny的光伏电池缺陷检测算法PSD-YOLO，在YOLOv7-tiny中引入轻量化卷积模块PSDConv。将GSConv中的DW卷积替换为Partial卷积，降低了内存访问量并提高了检测速度；并且引入了GhostNetv2中的解耦全连接注意力（DFC）机制，在保持其可部署性的同时提高了轻量级算法对光伏电池复杂缺陷类型的检测能力；在损失函数部分，将原本的CIoU替换为EIoU，加速了收敛且提高了回归精度。实验结果表明，PSD-YOLO模型在参数量和计算量方面分别相较于YOLOv7-tiny模型下降了18.3%和16.7%，模型大小仅有4.9×106，mAP@0.5提升了5.3个百分点，在实现更小模型体积的同时，达到了更高的检测性能。

关键词: YOLOv7-tiny, 光伏电池, 缺陷检测, 注意力机制, 损失函数

Abstract: To address the issue of unstable solar energy conversion efficiency in photovoltaic cells and improve the quality of photovoltaic cells, this article proposes a photovoltaic cell defect detection algorithm, PSD-YOLO, based on the improved YOLOv7-tiny with the introduction of the lightweight convolution module PSDConv. Initially, the DW (Depthwise) convolution in GSConv is replaced with Partial convolution, reducing memory access and improving detection speed. Additionally, the decoupled fully connected attention (DFC) mechanism from GhostNetv2 is incorporated, enhancing the capability of lightweight algorithms to detect complex defect types in photovoltaic cells while maintaining deployability. In the loss function section, CIoU is replaced with EIoU, accelerating convergence and improving regression accuracy. Experimental results demonstrate that the PSD-YOLO model reduces parameter and computational complexity by 18.3% and 16.7%, respectively, compared to the YOLOv7-tiny model. With a model size of only 4.9 million, it achieves a 5.3 percentage points improvement in mAP@0.5, attaining higher detection performance while achieving a smaller model size.

Key words: YOLOv7-tiny, solar cell, defect detection, attention mechanism, loss function

徐威, 李为相, 方志, 孙圆, 陈闯. 基于改进YOLOv7-tiny的光伏电池缺陷检测算法[J]. 计算机工程与应用, 2024, 60(15): 336-343.

XU Wei, LI Weixiang, FANG Zhi, SUN Yuan, CHEN Chuang. Solar Cell Defect Detection Algorithm Based on Improved YOLOv7-tiny[J]. Computer Engineering and Applications, 2024, 60(15): 336-343.

参考文献

[1] GIRSHICK R, DONAHUE J, DARRELL T, et al. Rich feature hierarchies for accurate object detection and semantic segmentation[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2014: 580-587.
[2] GIRSHICK R. Fast R-CNN[C]//Proceedings of the IEEE International Conference on Computer Vision, 2015: 1440-1448.
[3] HE K, GKIOXARI G, DOLLAR P, et al. Mask R-CNN[C]//Proceedings of the IEEE International Conference on Computer Vision, 2017: 2961-2969.
[4] REDMON J, DIVVALA S, GIRSHICK R, et al. You only look once: unified, real-time object detection[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016: 779-788.
[5] REDMON J, FARHADI A. Yolov3: an incremental improvement[J]. arXiv:1804.02767, 2018.
[6] BOCHKOVSKIY A, WANG C Y, LIAO H Y M. Yolov4: optimal speed and accuracy of object detection[J]. arXiv:2004.
10934, 2020.
[7] 窦智, 胡晨光, 李庆华, 等. 改进YOLOv7的小样本钢板表面缺陷检测算法[J]. 计算机工程与应用, 2023, 59(23): 283-292.
DOU Z, HU C G, LI Q H, et al. Improved YOLOv7 algorithm for small sample steel plate surface defect detection[J]. Computer Engineering and Applications, 2023, 59(23): 283-292.
[8] 赵春华, 罗顺, 谭金铃, 等. 基于PC-YOLOv7算法钢材表面缺陷检测[J]. 国外电子测量技术, 2023, 42(9): 137-145.
ZHAO C H, LUO S, TAN J L, et al. Detection of steel surface defects based on PC-YOLOv7 algorithm[J]. Foreign Electronic Measurement Technology, 2023, 42(9): 137-145.
[9] 冷浩, 夏骄雄. 基于改进YOLOv7的金属表面缺陷检测方法[J]. 计算机时代, 2023(9): 48-53.
LENG H, XIA J X. Metal surface defect detection method based on improved YOLOv7[J]. Computer Era, 2023(9): 48-53.
[10] 齐向明, 董旭. 改进Yolov7-tiny的钢材表面缺陷检测算法[J]. 计算机工程与应用, 2023, 59(12): 176-183.
QI X M, DONG X. Improved Yolov7-tiny algorithm for steel surface defect detection[J]. Computer Engineering and Applications, 2023, 59(12): 176-183.
[11] WANG C Y, BOCHKOVSKIY A, LIAO H Y M. YOLOv7: trainable bag-of-freebies sets new state-of-the-art for real-time object detec-tors[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023: 7464-7475.
[12] LI H, LI J, WEI H, et al. Slim-neck by GSConv: a better design paradigm of detector architectures for autonomous vehicles[J]. arXiv:2206.02424, 2022.
[13] TANG Y, HAN K, GUO J, et al. GhostNetv2: enhance cheap operation with long-range attention[C]//Advances in Neural Information Processing Systems, 2022: 9969-9982.
[14] ZHENG Z, WANG P, LIU W, et al. Distance-IoU loss: faster and better learning for bounding box regression[C]//Proceedings of the AAAI Conference on Artificial Intelligence, 2020: 12993-13000.
[15] HOWARD A G, ZHU M, CHEN B, et al. Mobilenets: efficient convolutional neural networks for mobile vision applications[J]. arXiv:1704.04861, 2017.
[16] MA N, ZHANG X, ZHENG H T, et al. Shufflenet v2: practical guidelines for efficient CNN architecture design[C]//Proceedings of the European Conference on Computer Vision (ECCV), 2018: 116-131.
[17] CHEN J, KAO S, HE H, et al. Run, don’t walk: chasing higher FLOPS for faster neural networks[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023: 12021-12031.
[18] BAHDANAU D, CHO K, BENGIO Y. Neural machine translation by jointly learning to align and translate[J]. arXiv:1409.0473, 2014.
[19] ZHANG D, ZHENG Z, LI M, et al. CSART: channel and spatial attention-guided residual learning for real-time object tracking[J]. Neurocomputing, 2021, 436: 260-272.
[20] HADSELL R, CHOPRA S, LECUN Y. Dimensionality reduction by learning an invariant mapping[C]//2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR’06), 2006: 1735-1742.
[21] SCHROFF F, KALENICHENKO D, PHILBIN J. Facenet: a unified embedding for face recognition and clustering[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2015: 815-823.
[22] WEN Y, ZHANG K, LI Z, et al. A discriminative feature learning approach for deep face recognition[C]//Proceedings of the 14th European Conference on Computer Vision, Amsterdam, The Netherlands, October 11-14, 2016. [S.l.]: Springer International Publishing, 2016: 499-515.
[23] WANG H, WANG Y, ZHOU Z, et al. Cosface: large margin cosine loss for deep face recognition[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018: 5265-5274.
[24] YU J, JIANG Y, WANG Z, et al. Unitbox: an advanced object detection network[C]//Proceedings of the 24th ACM International Conference on Multimedia, 2016: 516-520.
[25] REZATOFIGHI H, TSOI N, GWAK J Y, et al. Generalized intersection over union: a metric and a loss for bounding box regression[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2019: 658-666.
[26] GEVORGYAN Z. SIoU loss: more powerful learning for bounding box regression[J]. arXiv:2205.12740, 2022.
[27] HENDRYCKS D, GIMPEL K. Gaussian error linear units (gelus)[J]. arXiv:1606.08415, 2016.
[28] EVERINGHAM M, VAN G L, WILLIAMS C K I, et al. The pascal visual object classes (voc) challenge[J]. International Journal of Computer Vision, 2010, 88: 303-338.