{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,9]],"date-time":"2026-05-09T00:17:17Z","timestamp":1778285837810,"version":"3.51.4"},"reference-count":47,"publisher":"Institution of Engineering and Technology (IET)","issue":"1","license":[{"start":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T00:00:00Z","timestamp":1750118400000},"content-version":"vor","delay-in-days":167,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"content-domain":{"domain":["ietresearch.onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["IET Image Processing"],"published-print":{"date-parts":[[2025,1]]},"abstract":"<jats:title>ABSTRACT<\/jats:title>\n                  <jats:p>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\u2010YOLO, based on YOLOv8. The model improves the performance through the following improvements: first, the SPD\u2010Conv module is introduced to replace the traditional convolution in the backbone and neck sections to reduce the information loss caused by excessive down\u2010sampling, thus enhancing the detection of small targets. Second, the neck section C2f\u2010EMA 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\u2010DETR, YOLOv9s, YOLOv10n, and YOLOv11), the detection accuracies in terms of overall and small\u2010target defects are significantly improved, which further validates the effectiveness of the model.<\/jats:p>","DOI":"10.1049\/ipr2.70134","type":"journal-article","created":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T07:36:11Z","timestamp":1750145771000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["SEM\u2010YOLO: A Small Target Defect Detection Model for Photovoltaic Modules"],"prefix":"10.1049","volume":"19","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-5734-7826","authenticated-orcid":false,"given":"Wang","family":"Yun","sequence":"first","affiliation":[{"name":"Taiyuan University of Science and Technology  Taiyuan Shanxi China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yin","family":"Wang","sequence":"additional","affiliation":[{"name":"Taiyuan University of Science and Technology  Taiyuan Shanxi China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gang","family":"Xie","sequence":"additional","affiliation":[{"name":"Taiyuan University of Science and Technology  Taiyuan Shanxi China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhicheng","family":"Zhao","sequence":"additional","affiliation":[{"name":"Taiyuan University of Science and Technology  Taiyuan Shanxi China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"265","published-online":{"date-parts":[[2025,6,17]]},"reference":[{"key":"e_1_2_10_2_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.esr.2019.01.006"},{"key":"e_1_2_10_3_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.energy.2019.03.092"},{"key":"e_1_2_10_4_1","doi-asserted-by":"crossref","unstructured":"R.Girshick \u201cFast R\u2010cnn \u201dProceedings of the IEEE international conference on computer vision(2015):1440\u20131448.","DOI":"10.1109\/ICCV.2015.169"},{"key":"e_1_2_10_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"e_1_2_10_6_1","doi-asserted-by":"crossref","unstructured":"K.He G.Gkioxari P.Doll\u00e1r andR.Girshick \u201cMask R\u2010CNN \u201d inProceedings of the IEEE International Conference on Computer Vision (ICCV)(2017):2961\u20132969.","DOI":"10.1109\/ICCV.2017.322"},{"key":"e_1_2_10_7_1","doi-asserted-by":"crossref","unstructured":"J.Redmon \u201cYou Only Look Once: Unified Real\u2010Time Object Detection \u201d inProceedings of the IEEE Conference on Computer Vision and Pattern Recognition(CVPR)(2016).","DOI":"10.1109\/CVPR.2016.91"},{"key":"e_1_2_10_8_1","doi-asserted-by":"crossref","unstructured":"J.Redmon andA.Farhadi \u201cYOLO9000: Better Faster Stronger \u201d inProceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)(2017):7263\u20137271.","DOI":"10.1109\/CVPR.2017.690"},{"key":"e_1_2_10_9_1","unstructured":"J.Redmon \u201cYolov3: An Incremental Improvement \u201d arxiv preprint arxiv:1804.02767 (2018)."},{"key":"e_1_2_10_10_1","unstructured":"A.Bochkovskiy C. Y.Wang andH. Y. M.Liao \u201cYolov4: Optimal Speed and Accuracy of Object Detection \u201d arxiv preprint arxiv:2004.10934 (2020)."},{"key":"e_1_2_10_11_1","doi-asserted-by":"crossref","unstructured":"W.Liu D.Anguelov D.Erhan et\u00a0al. \u201cSSD: Single Shot Multibox Detector \u201d inComputer Vision\u2013ECCV 2016(2016):21\u201337.","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"e_1_2_10_12_1","doi-asserted-by":"publisher","DOI":"10.1002\/tee.23758"},{"key":"e_1_2_10_13_1","doi-asserted-by":"publisher","DOI":"10.3390\/s22155817"},{"key":"e_1_2_10_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIA.2022.3151560"},{"key":"e_1_2_10_15_1","doi-asserted-by":"crossref","unstructured":"X.Huang J.Zhu andY.Huo \u201cSSA\u2010YOLO: An Improved YOLO for Hot\u2010Rolled Strip Steel Surface Defect Detection \u201dIEEE Transactions on Instrumentation and Measurement2024.","DOI":"10.1109\/TIM.2024.3488136"},{"key":"e_1_2_10_16_1","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/TIM.2021.3056744","article-title":"SDDNet: A Fast and Accurate Network for Surface Defect Detection","volume":"70","author":"Cui L.","year":"2021","journal-title":"IEEE Transactions on Instrumentation and Measurement"},{"key":"e_1_2_10_17_1","doi-asserted-by":"crossref","unstructured":"X.Huang Y.Li Y.Bao andW.Zheng \u201cAdaptive Cross Transformer With Contrastive Learning for Surface Defect Detection \u201dIEEE Transactions on Instrumentation and Measurement2024.","DOI":"10.1109\/TIM.2024.3470998"},{"key":"e_1_2_10_18_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.measurement.2021.109185"},{"key":"e_1_2_10_19_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-024-75680-y"},{"key":"e_1_2_10_20_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.measurement.2023.112446"},{"key":"e_1_2_10_21_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-022-14971-8"},{"key":"e_1_2_10_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3325677"},{"key":"e_1_2_10_23_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2023.122669"},{"key":"e_1_2_10_24_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.autcon.2023.105062"},{"key":"e_1_2_10_25_1","doi-asserted-by":"publisher","DOI":"10.3390\/f14091812"},{"key":"e_1_2_10_26_1","unstructured":"S.Chen T.Cheng J.Fang et\u00a0al. \u201cTinyDet: Accurate Small Object Detection in Lightweight Generic Detectors \u201d arxiv preprint arxiv:2304.03428 (2023)."},{"key":"e_1_2_10_27_1","doi-asserted-by":"crossref","unstructured":"R.Sunkara andT.Luo \u201cNo More Strided Convolutions or Pooling: A New CNN Building Block for Low\u2010Resolution Images and Small Objects \u201d inJoint European conference on machine learning and Knowledge Discovery in Databases(2022):443\u2013459.","DOI":"10.1007\/978-3-031-26409-2_27"},{"key":"e_1_2_10_28_1","doi-asserted-by":"publisher","DOI":"10.3390\/app14041557"},{"key":"e_1_2_10_29_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2024.110714"},{"key":"e_1_2_10_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3416332"},{"key":"e_1_2_10_31_1","doi-asserted-by":"publisher","DOI":"10.1021\/tx000068s"},{"key":"e_1_2_10_32_1","doi-asserted-by":"crossref","unstructured":"Y.Zhao W.Lv S.Xu et\u00a0al. \u201cDetrs Beat Yolos on Real\u2010Time Object Detection \u201d inProceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)(2024):16965\u201316974.","DOI":"10.1109\/CVPR52733.2024.01605"},{"key":"e_1_2_10_33_1","doi-asserted-by":"crossref","unstructured":"C. Y.Wang I. H.Yeh andH. Y.Mark Liao \u201cYolov9: Learning What You Want to Learn Using Programmable Gradient Information \u201d inEuropean Conference on Computer Vision(2025):1\u201321.","DOI":"10.1007\/978-3-031-72751-1_1"},{"key":"e_1_2_10_34_1","first-page":"107984","article-title":"Yolov10: Real\u2010Time End\u2010to\u2010End Object Detection","volume":"37","author":"Wang A.","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_10_35_1","unstructured":"R.KhanamandM.Hussain \u201cYolov11: An Overview of the Key Architectural Enhancements \u201d arXiv preprint arXiv:2410.17725 (2024)."},{"key":"e_1_2_10_36_1","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/TIM.2024.3472791","article-title":"BED\u2010YOLO: An Enhanced YOLOv8 for High\u2010Precision Real\u2010Time Bearing Defect Detection","volume":"73","author":"Han T.","year":"2024","journal-title":"IEEE Transactions on Instrumentation and Measurement"},{"key":"e_1_2_10_37_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2024.107866"},{"key":"e_1_2_10_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/JSEN.2024.3419806"},{"key":"e_1_2_10_39_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.aej.2024.08.087"},{"key":"e_1_2_10_40_1","doi-asserted-by":"crossref","unstructured":"B.KhaliliandA. W.Smyth \u201cSOD\u2010YOLOv8\u2013Enhancing YOLOv8 for Small Object Detection in Traffic Scenes \u201d arxiv preprint arxiv:2408.04786 (2024).","DOI":"10.3390\/s24196209"},{"key":"e_1_2_10_41_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.tust.2024.105857"},{"key":"e_1_2_10_42_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.measurement.2024.115922"},{"key":"e_1_2_10_43_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11227-024-06121-w"},{"key":"e_1_2_10_44_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2024.127685"},{"key":"e_1_2_10_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3330844"},{"key":"e_1_2_10_46_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.sasc.2025.200193"},{"key":"e_1_2_10_47_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jksuci.2023.101670"},{"key":"e_1_2_10_48_1","doi-asserted-by":"crossref","unstructured":"S.Ren J.Song L.Yu S.Tian andJ.Long \u201cAn Improved YOLOv8 for Lesion Detection in Medical Images\u201d 2024 2nd International Conference on Machine Vision Image Processing & Imaging Technology (MVIPIT). IEEE 2024:167\u2013171.","DOI":"10.1109\/MVIPIT65697.2024.00037"}],"container-title":["IET Image Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/ietresearch.onlinelibrary.wiley.com\/doi\/pdf\/10.1049\/ipr2.70134","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/ietresearch.onlinelibrary.wiley.com\/doi\/full-xml\/10.1049\/ipr2.70134","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/ietresearch.onlinelibrary.wiley.com\/doi\/pdf\/10.1049\/ipr2.70134","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,8]],"date-time":"2026-05-08T23:58:27Z","timestamp":1778284707000},"score":1,"resource":{"primary":{"URL":"https:\/\/ietresearch.onlinelibrary.wiley.com\/doi\/10.1049\/ipr2.70134"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,1]]},"references-count":47,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2025,1]]}},"alternative-id":["10.1049\/ipr2.70134"],"URL":"https:\/\/doi.org\/10.1049\/ipr2.70134","archive":["Portico"],"relation":{},"ISSN":["1751-9659","1751-9667"],"issn-type":[{"value":"1751-9659","type":"print"},{"value":"1751-9667","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,1]]},"assertion":[{"value":"2024-12-24","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-06-06","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-06-17","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e70134"}}