由于光伏组件的电致发光（EL）缺陷存在微小、微弱的特点,导致EL图像缺陷检测是一项具有挑战性的任务,因此,提出多尺度编码互补注意力网络（MCECAN）。MCECAN的主干和预测头遵从YOLO系列设计,网络颈部应用多尺度编码互补注意力模块（MCECAM）。该模块前端利用多尺度编码器聚合多尺度信息、增强全局信息,后端互补坐标注意力建立特征图通道间的依赖关系,突出缺陷特征并抑制背景干扰,提高网络对微小、微弱目标的检测能力。在包含5537张EL图像的数据集上,该方法取得了优秀的检测性能。
Abstract
The defect detection for photovoltaic module electroluminescence images is a challenging task, due to two difficulties, tiny and weak. To address this problem, the Multi-Scale Encoding Complementary Attention Network （MCECAN） is designed. The backbone and prediction head of MCECAN follow the YOLO series design, but the network neck applies the Multi-Scale Coding Complementary Attention Module （MCECAM）. The front-end of the module uses a multi-scale encoder to aggregate multi-scale information and enhance global information. The back-end complementary coordinate attention establishes the dependency between feature map channels, highlights defect features, suppresses background interference, and improves the ability of network to detect tiny and weak targets. On a dataset containing 5537 EL defect images, the MCECAN shows the best detection performance.
关键词
光伏组件 /
缺陷检测 /
卷积神经网络 /
多尺度编码器 /
互补坐标注意力
Key words
photovoltaic modules /
defect detection /
convolutional neural network /
multi-scale encoder /
complementary coordinate attention
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] 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 multi-scale convolution neural network[J]. Acta energiae solaris sinica, 2022, 43(2): 211-216.
[2] SU B Y, CHEN H Y, CHEN P, et al.Deep learning-based solar-cell manufacturing defect detection with complementary attention network[J]. IEEE transactions on industrial informatics, 2021, 17(6): 4084-4095.
[3] SU B Y, CHEN H Y, ZHOU Z.BAF-detector: an efficient CNN-based detector for photovoltaic cell defect detection[J]. IEEE transactions on industrial electronics, 2022, 69(3): 3161-3171.
[4] 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.
[5] 周颖, 王如意, 袁梓桐, 等. 一种高效双路径注意力太阳电池缺陷检测网络[J]. 太阳能学报, 2023, 44(4): 407-413.
ZHOU Y, WANG R Y, YUAN Z T, et al.An efficient dual-path attention solar cell defect detection network[J]. Acta energiae solaris sinica, 2023, 44(4): 407-413.
[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] LIU W, ANGUELOV D, ERHAN D, et al.SSD: single shot MultiBox detector[M]//Computer Vision-ECCV 2016. Cham: Springer International Publishing, 2016: 21-37.
[8] 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.
[9] 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.
[10] GORDON D, KEMBHAVI A, RASTEGARI M, et al.IQA: visual question answering in interactive environments[C]//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City, UT, USA, 2018: 4089-4098.
[11] BOCHKOVSKIY A, WANG C Y, LIAO H.YOLOv4:optimal speed and accuracy of object detection[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Online, 2021: 13024-13033.
[12] SIMONYAN K, ZISSERMAN A. Very deep convolutional networks for large-scale image recognition[EB/OL].2014: arXiv: 1409.1556. https://arxiv.org/abs/1409.1556.
[13] HE K M, ZHANG X Y, REN S Q, et al.Deep residual learning for image recognition[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Las Vegas, NV, USA, 2016: 770-778.
[14] HUANG G, LIU Z, VAN DER MAATEN L, et al. Densely connected convolutional networks[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Honolulu, HI, USA, 2017: 2261-2269.
[15] WANG C Y, MARK LIAO H Y, WU Y 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). Seattle, WA, USA, 2020: 1571-1580.
[16] DOSOVITSKIY A, BEYER L, KOLESNIKOV A, et al. An image is worth 16x16 words: transformers for image recognition at scale[EB/OL].2020: arXiv: 2010.11929. https://arxiv.org/abs/2010.11929.
[17] CARION N, MASSA F, SYNNAEVE G, et al.End-to-end object detection with transformers[C]//Computer Vision-ECCV 2020: 16th European Conference, Glasgow, UK, Proceedings, Part I, 2020: 213-229.
[18] WANG H Y, ZHU Y K, ADAM H, et al.MaX-DeepLab: end-to-end panoptic segmentation with mask transformers[C]//2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Nashville, TN, USA, 2021: 5459-5470.
[19] 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.
基金
国家自然科学基金（U21A20482; 62073117）; 中央引导地方科技发展资金项目（206Z1701G）
PDF(2062 KB)
