SEM‐YOLO: A Small Target Defect Detection Model for Photovoltaic Modules

Wang Yun; Yin Wang; Gang Xie

doi:10.1049/ipr2.70134

journal article Open Access Jan 01, 2025

SEM‐YOLO: A Small Target Defect Detection Model for Photovoltaic Modules

Wang Yun

Yin Wang

Gang Xie

IET Image Processing Vol. 19 No. 1 · Institution of Engineering and Technology (IET)

View at Publisher Save 10.1049/ipr2.70134

Abstract

ABSTRACT
Defect detection is key to extending the lifetime of PV modules. However, existing methods still face significant challenges in detecting small and ambiguous targets. To this end, this paper proposes a PV module defect detection model, SEM‐YOLO, based on YOLOv8. The model improves the performance through the following improvements: first, the SPD‐Conv module is introduced to replace the traditional convolution in the backbone and neck sections to reduce the information loss caused by excessive down‐sampling, thus enhancing the detection of small targets. Second, the neck section C2f‐EMA module is introduced, in which the efficient multiscale attention module (EMA) enhances feature extraction by redistributing weights and prioritizing relevant features to improve the perception and recognition of small target defects (hot spots). Finally, we add a small target detection layer and increase the MultiSEAM detection header, so that the model can capture and detect small targets more efficiently at the output stage. The experimental results show that the mAP of the improved model reaches 93.8%, among which the mAP of small target defects reaches 83%, which is an improvement of 2.23% and 7.62% compared with YOLOv8. In addition, compared with the mainstream models (RT‐DETR, YOLOv9s, YOLOv10n, and YOLOv11), the detection accuracies in terms of overall and small‐target defects are significantly improved, which further validates the effectiveness of the model.

Topics

No keywords indexed for this article. Browse by subject →

References

47

[1]

The role of renewable energy in the global energy transformation

Dolf Gielen, Francisco Boshell, Deger Saygin et al.

Energy Strategy Reviews 10.1016/j.esr.2019.01.006

[2]

Status and perspectives on 100% renewable energy systems

Kenneth Hansen, Christian Breyer, Henrik Lund

Energy 10.1016/j.energy.2019.03.092

[3]

Fast R-CNN

Ross Girshick

2015 IEEE International Conference on Computer Vis... 10.1109/iccv.2015.169

[4]

Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks

Shaoqing Ren, Kaiming He, Ross Girshick et al.

IEEE Transactions on Pattern Analysis and Machine... 10.1109/tpami.2016.2577031

[5]

Mask R-CNN

Kaiming He, Georgia Gkioxari, Piotr Dollar et al.

2017 IEEE International Conference on Computer Vis... 10.1109/iccv.2017.322

[6]

You Only Look Once: Unified, Real-Time Object Detection

Joseph Redmon, Santosh Divvala, Ross Girshick et al.

2016 IEEE Conference on Computer Vision and Patter... 10.1109/cvpr.2016.91

[7]

YOLO9000: Better, Faster, Stronger

Joseph Redmon, Ali Farhadi

2017 IEEE Conference on Computer Vision and Patter... 10.1109/cvpr.2017.690

[8]

J.Redmon “Yolov3: An Incremental Improvement ” arxiv preprint arxiv:1804.02767 (2018).

[9]

A.Bochkovskiy C. Y.Wang andH. Y. M.Liao “Yolov4: Optimal Speed and Accuracy of Object Detection ” arxiv preprint arxiv:2004.10934 (2020).

[10]

SSD: Single Shot MultiBox Detector

Wei Liu, Dragomir Anguelov, Dumitru Erhan et al.

Lecture Notes in Computer Science 10.1007/978-3-319-46448-0_2

[11]

10.1002/tee.23758

[12]

10.3390/s22155817

[13]

10.1109/tia.2022.3151560

[14]

X.Huang J.Zhu andY.Huo “SSA‐YOLO: An Improved YOLO for Hot‐Rolled Strip Steel Surface Defect Detection ”IEEE Transactions on Instrumentation and Measurement2024. 10.1109/tim.2024.3488136

[15]

Cui L. "SDDNet: A Fast and Accurate Network for Surface Defect Detection" IEEE Transactions on Instrumentation and Measurement (2021) 10.1109/tim.2021.3056744

[16]

X.Huang Y.Li Y.Bao andW.Zheng “Adaptive Cross Transformer With Contrastive Learning for Surface Defect Detection ”IEEE Transactions on Instrumentation and Measurement2024. 10.1109/tim.2024.3470998

[17]

10.1016/j.measurement.2021.109185

[18]

10.1038/s41598-024-75680-y

[19]

10.1016/j.measurement.2023.112446

[20]

10.1038/s41598-022-14971-8

[21]

10.1109/access.2023.3325677

[22]

DsP-YOLO: An anchor-free network with DsPAN for small object detection of multiscale defects

Haifeng Zhang, Qingqing Huang, Yan Han et al.

Expert Systems with Applications 10.1016/j.eswa.2023.122669

[23]

10.1016/j.autcon.2023.105062

[24]

10.3390/f14091812

[25]

S.Chen T.Cheng J.Fang et al. “TinyDet: Accurate Small Object Detection in Lightweight Generic Detectors ” arxiv preprint arxiv:2304.03428 (2023).

[26]

R.Sunkara andT.Luo “No More Strided Convolutions or Pooling: A New CNN Building Block for Low‐Resolution Images and Small Objects ” inJoint European conference on machine learning and Knowledge Discovery in Databases(2022):443–459. 10.1007/978-3-031-26409-2_27

[27]

10.3390/app14041557

[28]

YOLO-FaceV2: A scale and occlusion aware face detector

Ziping Yu, Weijun Chen, Yongxin Su et al.

Pattern Recognition 10.1016/j.patcog.2024.110714

[29]

10.1109/access.2024.3416332

[30]

10.1021/tx000068s

[31]

Y.Zhao W.Lv S.Xu et al. “Detrs Beat Yolos on Real‐Time Object Detection ” inProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)(2024):16965–16974. 10.1109/cvpr52733.2024.01605

[32]

C. Y.Wang I. H.Yeh andH. Y.Mark Liao “Yolov9: Learning What You Want to Learn Using Programmable Gradient Information ” inEuropean Conference on Computer Vision(2025):1–21. 10.1007/978-3-031-72751-1_1

[33]

Wang A. "Yolov10: Real‐Time End‐to‐End Object Detection" Advances in Neural Information Processing Systems (2024)

[34]

R.KhanamandM.Hussain “Yolov11: An Overview of the Key Architectural Enhancements ” arXiv preprint arXiv:2410.17725 (2024).

[35]

Han T. "BED‐YOLO: An Enhanced YOLOv8 for High‐Precision Real‐Time Bearing Defect Detection" IEEE Transactions on Instrumentation and Measurement (2024) 10.1109/tim.2024.3472791

[36]

10.1016/j.engappai.2024.107866

[37]

10.1109/jsen.2024.3419806

[38]

10.1016/j.aej.2024.08.087

[39]

B.KhaliliandA. W.Smyth “SOD‐YOLOv8–Enhancing YOLOv8 for Small Object Detection in Traffic Scenes ” arxiv preprint arxiv:2408.04786 (2024). 10.3390/s24196209

[40]

10.1016/j.tust.2024.105857

[41]

10.1016/j.measurement.2024.115922

[42]

10.1007/s11227-024-06121-w

[43]

10.1016/j.neucom.2024.127685

[44]

10.1109/access.2023.3330844

[45]

10.1016/j.sasc.2025.200193

[46]

10.1016/j.jksuci.2023.101670

[47]

S.Ren J.Song L.Yu S.Tian andJ.Long “An Improved YOLOv8 for Lesion Detection in Medical Images” 2024 2nd International Conference on Machine Vision Image Processing & Imaging Technology (MVIPIT). IEEE 2024:167–171. 10.1109/mvipit65697.2024.00037

Metrics

2

Citations

47

References

Details

Published: Jan 01, 2025
Vol/Issue: 19(1)
License: View

Authors

W

Wang Yun

Taiyuan University of Science and Technology Taiyuan Shanxi China

Y

Yin Wang

Taiyuan University of Science and Technology Taiyuan Shanxi China

G

Gang Xie

Taiyuan University of Science and Technology Taiyuan Shanxi China

Cite This Article

Wang Yun, Yin Wang, Gang Xie (2025). SEM‐YOLO: A Small Target Defect Detection Model for Photovoltaic Modules. IET Image Processing, 19(1). https://doi.org/10.1049/ipr2.70134

SEM‐YOLO: A Small Target Defect Detection Model for Photovoltaic Modules

You May Also Like