{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,12]],"date-time":"2026-04-12T12:48:08Z","timestamp":1775998088387,"version":"3.50.1"},"reference-count":39,"publisher":"Springer Science and Business Media LLC","issue":"6","license":[{"start":{"date-parts":[[2024,7,17]],"date-time":"2024-07-17T00:00:00Z","timestamp":1721174400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2024,7,17]],"date-time":"2024-07-17T00:00:00Z","timestamp":1721174400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61573183"],"award-info":[{"award-number":["61573183"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100007128","name":"Natural Science Foundation of Shaanxi Province","doi-asserted-by":"publisher","award":["2024JC-YBQN-0695"],"award-info":[{"award-number":["2024JC-YBQN-0695"]}],"id":[{"id":"10.13039\/501100007128","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Complex Intell. Syst."],"published-print":{"date-parts":[[2024,12]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Defect detection for photovoltaic (PV) cell images is a challenging task due to the small size of the defect features and the complexity of the background characteristics. Modern detectors rely mostly on proxy learning objectives for prediction and on manual post-processing components. One-to-one set matching is a critical design for DEtection TRansformer (DETR) in order to provide end-to-end capability, so that does not need a hand-crafted Efficient Non-Maximum Suppression NMS. In order to detect PV cell defects faster and better, a technology called the PV cell Defects DEtection Transformer (PD-DETR) is proposed. To address the issue of slow convergence caused by DETR\u2019s direct translation of image feature mapping into target detection results, we created a hybrid feature module. To achieve a balance between performance and computation, the image features are passed through a scoring network and dilated convolution, respectively, to obtain the foreground fine feature and contour high-frequency feature. The two features are then adaptively intercepted and fused. The capacity of the model to detect small-scale defects under complex background conditions is improved by the addition of high-frequency information. Furthermore, too few positive queries will be assigned to the defect target via one-to-one set matching, which will result in sparse supervision of the encoder and impair the decoder\u2019s ability of attention learning. Consequently, we enhanced the detection effect by combining the original DETR with the one-to-many matching branch. Specifically, two Faster RCNN detection heads were added during training. To maintain the end-to-end benefits of DETR, inference is still performed using the original one-to-one set matching. Our model implements 64.7% AP on the PVEL-AD dataset.<\/jats:p>","DOI":"10.1007\/s40747-024-01559-0","type":"journal-article","created":{"date-parts":[[2024,7,17]],"date-time":"2024-07-17T04:01:52Z","timestamp":1721188912000},"page":"7421-7434","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":15,"title":["PD-DETR: towards efficient parallel hybrid matching with transformer for photovoltaic cell defects detection"],"prefix":"10.1007","volume":"10","author":[{"given":"Langyue","family":"Zhao","sequence":"first","affiliation":[]},{"given":"Yiquan","family":"Wu","sequence":"additional","affiliation":[]},{"given":"Yubin","family":"Yuan","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,7,17]]},"reference":[{"issue":"1","key":"1559_CR1","doi-asserted-by":"publisher","first-page":"122","DOI":"10.1109\/TII.2012.2209663","volume":"9","author":"DM Tsai","year":"2012","unstructured":"Tsai DM, Wu SC, Chiu WY (2012) Defect detection in solar modules using ICA basis images[J]. IEEE Trans Industr Inf 9(1):122\u2013131","journal-title":"IEEE Trans Industr Inf"},{"issue":"3","key":"1559_CR2","doi-asserted-by":"publisher","first-page":"3161","DOI":"10.1109\/TIE.2021.3070507","volume":"69","author":"B Su","year":"2021","unstructured":"Su B, Chen H, Zhou Z (2021) BAF-detector: an efficient CNN-based detector for photovoltaic cell defect detection[J]. IEEE Trans Industr Electron 69(3):3161\u20133171","journal-title":"IEEE Trans Industr Electron"},{"key":"1559_CR3","first-page":"1","volume":"71","author":"H Chen","year":"2022","unstructured":"Chen H, Song M, Zhang Z et al (2022) Detection of surface defects in solar cells by bidirectional-path feature pyramid group-wise attention detector[J]. IEEE Trans Instrum Meas 71:1\u20139","journal-title":"IEEE Trans Instrum Meas"},{"key":"1559_CR4","unstructured":"Soh LS, Ho HW Autonomous Navigation of Micro Air Vehicles in Warehouses using Vision-based line Following[J]. arXiv preprint arXiv:2310.00950, 2023."},{"key":"1559_CR5","doi-asserted-by":"crossref","unstructured":"Song X, Peng Z, Song S et al (2024) Anti-disturbance state estimation for PDT-switched RDNNs utilizing time-sampling and space-splitting measurements[J]. Commun Nonlinear Sci Numer Simul, : 107945","DOI":"10.1016\/j.cnsns.2024.107945"},{"key":"1559_CR6","doi-asserted-by":"publisher","first-page":"126498","DOI":"10.1016\/j.neucom.2023.126498","volume":"550","author":"X Song","year":"2023","unstructured":"Song X, Wu N, Song S et al (2023) Bipartite synchronization for cooperative-competitive neural networks with reaction\u2013diffusion terms via dual event-triggered mechanism[J]. Neurocomputing 550:126498","journal-title":"Neurocomputing"},{"key":"1559_CR7","first-page":"1","volume":"71","author":"J Yu","year":"2021","unstructured":"Yu J, Cheng X, Li Q (2021) Surface defect detection of steel strips based on anchor-free network with channel attention and bidirectional feature fusion[J]. IEEE Trans Instrum Meas 71:1\u201310","journal-title":"IEEE Trans Instrum Meas"},{"key":"1559_CR8","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/TIM.2020.2991573","volume":"70","author":"X Cheng","year":"2020","unstructured":"Cheng X, Yu J (2020) RetinaNet with difference channel attention and adaptively spatial feature fusion for steel surface defect detection[J]. IEEE Trans Instrum Meas 70:1\u201311","journal-title":"IEEE Trans Instrum Meas"},{"key":"1559_CR9","doi-asserted-by":"publisher","unstructured":"Kang H, Hong J, Lee J, Kang S (2024) Photovoltaic cell defect detection based on weakly supervised Learning with Module-Level Annotations[J]. IEEE Access 125575\u20135583. https:\/\/doi.org\/10.1109\/ACCESS.2024.3349975","DOI":"10.1109\/ACCESS.2024.3349975"},{"key":"1559_CR10","doi-asserted-by":"crossref","unstructured":"Wang T, Yuan L, Chen Y et al (2021) Pnp-detr: Towards efficient visual analysis with transformers[C]\/\/Proceedings of the IEEE\/CVF international conference on computer vision. : 4661\u20134670","DOI":"10.1109\/ICCV48922.2021.00462"},{"key":"1559_CR11","doi-asserted-by":"crossref","unstructured":"Girshick R (2015) Fast r-cnn[C]\/\/Proceedings of the IEEE international conference on computer vision. : 1440\u20131448","DOI":"10.1109\/ICCV.2015.169"},{"key":"1559_CR12","first-page":"5998","volume":"30","author":"A Vaswani","year":"2017","unstructured":"Vaswani A, Shazeer N, Parmar N et al (2017) Attention is all you need[J]. Adv Neural Inf Process Syst 30:5998\u20136008","journal-title":"Adv Neural Inf Process Syst"},{"key":"1559_CR13","doi-asserted-by":"crossref","unstructured":"Carion N, Massa F, Synnaeve G et al (2020) End-to-end object detection with transformers[C]\/\/ European conference on computer vision. Cham: Springer International Publishing, : 213\u2013229","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"1559_CR14","unstructured":"Choromanski K, Likhosherstov V, Dohan D et al (2020) Rethinking attention with performers[J]. arXiv preprint arXiv:2009.14794"},{"key":"1559_CR15","unstructured":"Katharopoulos A, Vyas A, Pappas N et al (2020) Transformers are rnns: Fast autoregressive transformers with linear attention[C]\/\/ International conference on machine learning. PMLR, : 5156\u20135165"},{"key":"1559_CR16","unstructured":"Kitaev N, Kaiser \u0141, Levskaya A, Reformer (2020) The efficient transformer[J]. arXiv preprint arXiv:2001.04451"},{"key":"1559_CR17","unstructured":"Wang S, Li BZ, Khabsa M et al (2020) Linformer: Self-attention with linear complexity[J]. arXiv preprint arXiv:2006.04768"},{"issue":"6","key":"1559_CR18","doi-asserted-by":"publisher","first-page":"1137","DOI":"10.1109\/TPAMI.2016.2577031","volume":"39","author":"S Ren","year":"2016","unstructured":"Ren S, He K, Girshick R et al (2016) Faster R-CNN: towards real-time object detection with region proposal networks[J]. IEEE Trans Pattern Anal Mach Intell 39(6):1137\u20131149","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"1559_CR19","doi-asserted-by":"crossref","unstructured":"Lin TY, Goyal P, Girshick R et al (2017) Focal loss for dense object detection[C]\/\/ Proceedings of the IEEE international conference on computer vision. : 2980\u20132988","DOI":"10.1109\/ICCV.2017.324"},{"key":"1559_CR20","doi-asserted-by":"crossref","unstructured":"Wang J, Song L, Li Z et al (2021) End-to-end object detection with fully convolutional network[C]\/\/ Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. : 15849\u201315858","DOI":"10.1109\/CVPR46437.2021.01559"},{"key":"1559_CR21","doi-asserted-by":"crossref","unstructured":"Zhi Tian C, Shen H, Chen et al (2019) Fcos: Fully convolutional one-stage object detection[C]\/\/ Proceedings of the IEEE international conference on computer vision. : 9627\u20139636","DOI":"10.1109\/ICCV.2019.00972"},{"key":"1559_CR22","doi-asserted-by":"crossref","unstructured":"Zhang S, Chi C, Yao Y et al (2020) Bridging the gap between anchor-based and anchor-free detection via adaptive training sample selection[C]\/\/ Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. : 9759\u20139768","DOI":"10.1109\/CVPR42600.2020.00978"},{"key":"1559_CR23","doi-asserted-by":"crossref","unstructured":"Kim K, Lee HS (2020) Probabilistic anchor assignment with iou prediction for object detection[C]\/\/ Computer Vision\u2013ECCV. : 16th European Conference, Glasgow, UK, August 23\u201328, 2020, Proceedings, Part XXV 16. Springer International Publishing, 2020: 355\u2013371","DOI":"10.1007\/978-3-030-58595-2_22"},{"key":"1559_CR24","doi-asserted-by":"crossref","unstructured":"Tian S, Li W, Li S et al (2021) Image defect detection and segmentation algorithm of solar cell based on convolutional neural network[C]\/\/ 2021 6th International Conference on Intelligent Computing and Signal Processing (ICSP). IEEE, : 154\u2013157","DOI":"10.1109\/ICSP51882.2021.9408827"},{"key":"1559_CR25","doi-asserted-by":"publisher","first-page":"116319","DOI":"10.1016\/j.energy.2019.116319","volume":"189","author":"MW Akram","year":"2019","unstructured":"Akram MW, Li G, Jin Y et al (2019) CNN based automatic detection of photovoltaic cell defects in electroluminescence images[J]. Energy 189:116319","journal-title":"Energy"},{"issue":"24","key":"1559_CR26","doi-asserted-by":"publisher","first-page":"6496","DOI":"10.3390\/en13246496","volume":"13","author":"R Pierdicca","year":"2020","unstructured":"Pierdicca R, Paolanti M, Felicetti A et al (2020) Automatic faults detection of photovoltaic farms: solAIr, a deep learning-based system for thermal images[J]. Energies 13(24):6496","journal-title":"Energies"},{"issue":"6","key":"1559_CR27","doi-asserted-by":"publisher","first-page":"4084","DOI":"10.1109\/TII.2020.3008021","volume":"17","author":"B Su","year":"2020","unstructured":"Su B, Chen H, Chen P et al (2020) Deep learning-based solar-cell manufacturing defect detection with complementary attention network[J]. IEEE Trans Industr Inf 17(6):4084\u20134095","journal-title":"IEEE Trans Industr Inf"},{"key":"1559_CR28","unstructured":"Zhu X, Su W, Lu L et al Deformable detr: deformable transformers for end-to-end object detection[J]. arXiv preprint arXiv:2010.04159, 2020."},{"key":"1559_CR29","doi-asserted-by":"crossref","unstructured":"Meng D, Chen X, Fan Z et al (2021) Conditional detr for fast training convergence[C]\/\/ Proceedings of the IEEE\/CVF international conference on computer vision. : 3651\u20133660","DOI":"10.1109\/ICCV48922.2021.00363"},{"key":"1559_CR30","doi-asserted-by":"crossref","unstructured":"Wang Y, Zhang X, Yang T et al (2022) Anchor detr: Query design for transformer-based detector[C]\/\/ Proceedings of the AAAI conference on artificial intelligence. 36(3): 2567\u20132575","DOI":"10.1609\/aaai.v36i3.20158"},{"key":"1559_CR31","unstructured":"Liu S, Li F, Zhang H et al Dab-detr: dynamic anchor boxes are better queries for detr[J]. arXiv preprint arXiv:2201.12329, 2022."},{"key":"1559_CR32","doi-asserted-by":"crossref","unstructured":"Li F, Zhang H, Liu S et al (2022) Dn-detr: Accelerate detr training by introducing query denoising[C]\/ \/Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. : 13619\u201313627","DOI":"10.1109\/CVPR52688.2022.01325"},{"key":"1559_CR33","unstructured":"Zhang H, Li F, Liu S et al (2022) Dino: Detr with improved denoising anchor boxes for end-to-end object detection[J]. arXiv preprint arXiv:2203.03605"},{"issue":"3","key":"1559_CR34","first-page":"12","volume":"2","author":"Q Chen","year":"2022","unstructured":"Chen Q, Chen X, Zeng G et al (2022) Group detr: fast training convergence with decoupled one-to-many label assignment[J]. arXiv Preprint arXiv:2207 13085 2(3):12","journal-title":"arXiv Preprint arXiv:2207 13085"},{"key":"1559_CR35","doi-asserted-by":"crossref","unstructured":"Jia D, Yuan Y, He H et al (2023) Detrs with hybrid matching[C]\/\/ Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. : 19702\u201319712","DOI":"10.1109\/CVPR52729.2023.01887"},{"key":"1559_CR36","doi-asserted-by":"crossref","unstructured":"Xu K, Yang X, Yin B et al (2020) Learning to restore low-light images via decomposition-and-enhancement[C]\/\/ Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. : 2281\u20132290","DOI":"10.1109\/CVPR42600.2020.00235"},{"issue":"1","key":"1559_CR37","doi-asserted-by":"publisher","first-page":"404","DOI":"10.1109\/TII.2022.3162846","volume":"19","author":"B Su","year":"2022","unstructured":"Su B, Zhou Z, Chen H (2022) PVEL-AD: a large-scale open-world dataset for photovoltaic cell anomaly detection[J]. IEEE Trans Industr Inf 19(1):404\u2013413","journal-title":"IEEE Trans Industr Inf"},{"key":"1559_CR38","first-page":"21002","volume":"33","author":"X Li","year":"2020","unstructured":"Li X, Wang W, Wu L et al (2020) Generalized focal loss: learning qualified and distributed bounding boxes for dense object detection[J]. Adv Neural Inf Process Syst 33:21002\u201321012","journal-title":"Adv Neural Inf Process Syst"},{"key":"1559_CR39","doi-asserted-by":"crossref","unstructured":"Liu Z, Lin Y, Cao Y et al (2021) Swin transformer: Hierarchical vision transformer using shifted windows[C]\/\/ Proceedings of the IEEE\/CVF international conference on computer vision. : 10012\u201310022","DOI":"10.1109\/ICCV48922.2021.00986"}],"container-title":["Complex &amp; Intelligent Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s40747-024-01559-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s40747-024-01559-0\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s40747-024-01559-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,16]],"date-time":"2024-10-16T22:06:39Z","timestamp":1729116399000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s40747-024-01559-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,17]]},"references-count":39,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2024,12]]}},"alternative-id":["1559"],"URL":"https:\/\/doi.org\/10.1007\/s40747-024-01559-0","relation":{},"ISSN":["2199-4536","2198-6053"],"issn-type":[{"value":"2199-4536","type":"print"},{"value":"2198-6053","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,7,17]]},"assertion":[{"value":"25 February 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 July 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 July 2024","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"No potential conflict of interest was reported by the authors.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}