{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,17]],"date-time":"2026-04-17T01:04:08Z","timestamp":1776387848403,"version":"3.51.2"},"reference-count":48,"publisher":"MDPI AG","issue":"5","license":[{"start":{"date-parts":[[2025,4,28]],"date-time":"2025-04-28T00:00:00Z","timestamp":1745798400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100004775","name":"Natural Science Foundation of Gansu Province","doi-asserted-by":"publisher","award":["22JR11RA160"],"award-info":[{"award-number":["22JR11RA160"]}],"id":[{"id":"10.13039\/501100004775","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Symmetry"],"abstract":"<jats:p>Railway catenary layout drawings (RCLDs) have the characteristics of upper and lower symmetry, a large drawing size, a small size, high similarity among target symbols, and an uneven distribution of symbol categories. These factors make the symbol detection task more complex and challenging. To address the aforementioned challenges, this paper proposes three enhancements to YOLOv8n to improve symbol detection performance and integrates an improved denoising diffusion probabilistic model (IDDPM) to mitigate the imbalance in symbol category distribution. First, the multi-scale dilated attention (MSDA) is introduced in the Neck part to enhance the model\u2019s perception of the global context in complex RCLD scenes, so that it can more effectively capture the symbol information distributed in different scales and backgrounds. Secondly, the receptive field attention convolution (RFAConv) is used in the detection head to replace the standard convolution, to improve the ability to focus on the target symbols in RCLDs and effectively alleviate the occlusion interference between symbols. Finally, the dynamic upsampler (DySample) is used to enhance the clarity and positioning accuracy of the edge area of small target symbols in RCLDs and enhance the detection of small targets. The above design made targeted optimizations to resolve the problems of symbol and background interference, character overlap, and symbol category imbalances in complex scenes in RCLDs, effectively improving the overall detection performance of the model. Compared with the baseline YOLOv8n model, the improved YOLOv8n achieves increases of 2.9% in F1, 1.9% in mAP@0.5, and 1.7% in mAP@0.5:0.95. With the introduction of synthetic data, the recognition of minority-class symbols is further enhanced, leading to additional gains of 4%, 3.8%, and 14% in F1, mAP@0.5, and mAP@0.5:0.95, respectively. These results demonstrate the effectiveness and superiority of the proposed method in improving detection performance.<\/jats:p>","DOI":"10.3390\/sym17050674","type":"journal-article","created":{"date-parts":[[2025,5,2]],"date-time":"2025-05-02T11:35:13Z","timestamp":1746185713000},"page":"674","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Symbol Recognition Method for Railway Catenary Layout Drawings Based on Deep Learning"],"prefix":"10.3390","volume":"17","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-2477-0516","authenticated-orcid":false,"given":"Qi","family":"Sun","sequence":"first","affiliation":[{"name":"Railroad Industry Key Laboratory of Four Electric BIM Engineering and Intelligent Application, Lanzhou Jiaotong University, Lanzhou 730070, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-6257-4034","authenticated-orcid":false,"given":"Mengxin","family":"Zhu","sequence":"additional","affiliation":[{"name":"School of Electronics and Information Engineering, Lanzhou Jiaotong University, Lanzhou 730070, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Minzhi","family":"Li","sequence":"additional","affiliation":[{"name":"School of Electronics and Information Engineering, Lanzhou Jiaotong University, Lanzhou 730070, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gaoju","family":"Li","sequence":"additional","affiliation":[{"name":"China Railway Signal and Communication Research and Design Institute Group Co., Ltd., Beijing 100070, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Weizhi","family":"Deng","sequence":"additional","affiliation":[{"name":"Railroad Industry Key Laboratory of Four Electric BIM Engineering and Intelligent Application, Lanzhou Jiaotong University, Lanzhou 730070, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2025,4,28]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"3137","DOI":"10.1109\/TTE.2021.3078215","article-title":"Risk assessment for electrified railway catenary system under comprehensive influence of geographical and meteorological factors","volume":"7","author":"Feng","year":"2021","journal-title":"IEEE Trans. Transp. Electrif."},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Paliwal, S., Jain, A., Sharma, M., and Vig, L. (2021, January 11). Digitize-PID: Automatic digitization of piping and instrumentation diagrams. Proceedings of the Trends and Applications in Knowledge Discovery and Data Mining: PAKDD 2021 Workshops, WSPA, MLMEIN, SDPRA, DARAI, and AI4EPT, Delhi, India.","DOI":"10.1007\/978-3-030-75015-2_17"},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Paliwal, S., Sharma, M., and Vig, L. (2021, January 18\u201322). OSSR-PID: One-shot symbol recognition in P&ID sheets using path sampling and GCN. Proceedings of the 2021 International Joint Conference on Neural Networks (IJCNN), Shenzhen, China.","DOI":"10.1109\/IJCNN52387.2021.9534122"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"331","DOI":"10.1109\/34.3898","article-title":"An automatic circuit diagram reader with loop-structure-based symbol recognition","volume":"10","author":"Okazaki","year":"1988","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"709","DOI":"10.1142\/S0219467807002878","article-title":"Recognition of engineering drawing entities: Review of approaches","volume":"7","author":"Ablameyko","year":"2007","journal-title":"Int. J. Image Graph."},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Kang, S.O., Lee, E.B., and Baek, H.K. (2019). A digitization and conversion tool for imaged drawings to intelligent piping and instrumentation diagrams (P&ID). Energies, 12.","DOI":"10.3390\/en12132593"},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Nurminen, J.K., Rainio, K., Numminen, J.P., Syrj\u00e4nen, T., Paganus, N., and Honkoila, K. (2020, January 20\u201322). Object detection in design diagrams with machine learning. Proceedings of the 11th International Conference on Computer Recognition Systems (CORES 2019), Polanica Zdroj, Poland.","DOI":"10.1007\/978-3-030-19738-4_4"},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Manakitsa, N., Maraslidis, G.S., Moysis, L., and Fragulis, G.F. (2024). A review of machine learning and deep learning for object detection, semantic segmentation, and human action recognition in machine and robotic vision. Technologies, 12.","DOI":"10.3390\/technologies12020015"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"1695","DOI":"10.1007\/s00521-018-3583-1","article-title":"New trends on digitisation of complex engineering drawings","volume":"31","author":"Elyan","year":"2019","journal-title":"Neural Comput. Appl."},{"key":"ref_10","first-page":"397","article-title":"Current state and predicted technological trends in global railway intelligent digital transformation","volume":"2","author":"Li","year":"2023","journal-title":"Railw. Sci."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Nguyen, M.T., Pham, V.L., Nguyen, C.C., and Nguyen, V.V. (2021, August 15). Object Detection and Text Recognition in Large-Scale Technical Drawings. Available online: https:\/\/eprints.uet.vnu.edu.vn\/eprints\/id\/eprint\/4603\/.","DOI":"10.5220\/0010314406120619"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Faltin, B., Sch\u00f6nfelder, P., and K\u00f6nig, M. (2023). Inferring interconnections of construction drawings for bridges using deep learning-based methods. ECPPM 2022-eWork and eBusiness in Architecture, Engineering and Construction 2022, CRC Press.","DOI":"10.1201\/9781003354222-44"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Francois, M., Eglin, V., and Biou, M. (2022, January 22\u201325). Text detection and post-OCR correction in engineering documents. Proceedings of the International Workshop on Document Analysis Systems, La Rochelle, France.","DOI":"10.1007\/978-3-031-06555-2_49"},{"key":"ref_14","unstructured":"Sarkar, S., Pandey, P., and Kar, S. (2022). Automatic detection and classification of symbols in engineering drawings. arXiv."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"103442","DOI":"10.1016\/j.compind.2021.103442","article-title":"Extraction of dimension requirements from engineering drawings for supporting quality control in production processes","volume":"129","author":"Scheibel","year":"2021","journal-title":"Comput. Ind."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"136","DOI":"10.1007\/s10462-024-10779-2","article-title":"A review of deep learning methods for digitisation of complex documents and engineering diagrams","volume":"57","author":"Jamieson","year":"2024","journal-title":"Artif. Intell. Rev."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"1137","DOI":"10.1109\/TPAMI.2016.2577031","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","volume":"39","author":"Ren","year":"2016","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., and Girshick, R. (2017, January 22\u201329). Mask r-cnn. Proceedings of the IEEE International Conference on Computer Vision, Venice, Italy.","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Redmon, J. (2016, January 27\u201330). You only look once: Unified, real-time object detection. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.91"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, C.Y., and Berg, A.C. (2016, January 11\u201314). Ssd: Single shot multibox detector. Proceedings of the Computer Vision\u2014ECCV 2016: 14th European Conference, Amsterdam, The Netherlands.","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., and Zagoruyko, S. (2020, January 23\u201328). End-to-end object detection with transformers. Proceedings of the European Conference on Computer Vision, Glasgow, UK.","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref_22","unstructured":"Bochkovskiy, A., Wang, C.Y., and Liao, H.Y.M. (2020). Yolov4: Optimal speed and accuracy of object detection. arXiv."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"108490","DOI":"10.1016\/j.compeleceng.2022.108490","article-title":"An improved algorithm for small object detection based on YOLO v4 and multi-scale contextual information","volume":"105","author":"Ji","year":"2023","journal-title":"Comput. Electr. Eng."},{"key":"ref_24","unstructured":"Ultralytics (2024, November 01). YOLOv8. Available online: https:\/\/github.com\/ultralytics\/ultralytics."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"109021","DOI":"10.1016\/j.compeleceng.2023.109021","article-title":"An efficient detection of non-standard miner behavior using improved YOLOv8","volume":"112","author":"Wang","year":"2023","journal-title":"Comput. Electr. Eng."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"156003","DOI":"10.1109\/ACCESS.2024.3482102","article-title":"YOLO-CXR: A novel detection network for locating multiple small lesions in chest X-ray images","volume":"12","author":"Hao","year":"2024","journal-title":"IEEE Access"},{"key":"ref_27","unstructured":"Tan, W.C., Chen, I.M., and Tan, H.K. (2016, January 21\u201324). Automated identification of components in raster piping and instrumentation diagram with minimal pre-processing. Proceedings of the 2016 IEEE International Conference on Automation Science and Engineering (CASE), Fort Worth, TX, USA."},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Moreno-Garc\u00eda, C.F., Elyan, E., and Jayne, C. (2017, January 25\u201327). Heuristics-based detection to improve text\/graphics segmentation in complex engineering drawings. Proceedings of the Engineering Applications of Neural Networks: 18th International Conference, EANN 2017, Athens, Greece.","DOI":"10.1007\/978-3-319-65172-9_8"},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Moon, Y., Lee, J., Mun, D., and Lim, S. (2021). Deep learning-based method to recognize line objects and flow arrows from image-format piping and instrumentation diagrams for digitization. Appl. Sci., 11.","DOI":"10.3390\/app112110054"},{"key":"ref_30","first-page":"8","article-title":"Symbol Detection in a Multi-class Dataset Based on Single Line Diagrams using Deep Learning Models","volume":"14","author":"Bhanbhro","year":"2023","journal-title":"Int. J. Adv. Comput. Sci. Appl."},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Su, G., Zhao, S., Li, T., Liu, S., Li, Y., Zhao, G., and Li, Z. (2024). Image format pipeline and instrument diagram recognition method based on deep learning. Biomim. Intell. Robot., 4.","DOI":"10.1016\/j.birob.2023.100142"},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"122389","DOI":"10.1016\/j.eswa.2023.122389","article-title":"Practical single-line diagram recognition based on digital image processing and deep vision models","volume":"238","author":"Yang","year":"2024","journal-title":"Expert Syst. Appl."},{"key":"ref_33","first-page":"2513","article-title":"A Review of Neural Network Approach on Engineering Drawing Recognition and Future Directions","volume":"7","author":"Yazed","year":"2023","journal-title":"JOIV Int. J. Inform. Vis."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"91","DOI":"10.1016\/j.neunet.2020.05.025","article-title":"Deep learning for symbols detection and classification in engineering drawings","volume":"129","author":"Elyan","year":"2020","journal-title":"Neural Netw."},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Bhanbhro, H., Kwang Hooi, Y., Kusakunniran, W., and Amur, Z.H. (2023). A Symbol Recognition System for Single-Line Diagrams Developed Using a Deep-Learning Approach. Appl. Sci., 13.","DOI":"10.3390\/app13158816"},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"187","DOI":"10.1016\/j.neunet.2021.07.019","article-title":"Adversarial text-to-image synthesis: A review","volume":"144","author":"Frolov","year":"2021","journal-title":"Neural Netw."},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Moser, B., Shanbhag, A., Raue, F., Frolov, S., Palacio, S., and Dengel, A. (2024). Diffusion models in image super-resolution and everything: A survey. arXiv.","DOI":"10.1109\/TNNLS.2024.3476671"},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"10850","DOI":"10.1109\/TPAMI.2023.3261988","article-title":"Diffusion models in vision: A survey","volume":"45","author":"Croitoru","year":"2023","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_39","unstructured":"Bhunia, A.K., Khan, S., Cholakkal, H., Anwer, R.M., Laaksonen, J., Shah, M., and Khan, F.S. (2023, January 17\u201324). Person image synthesis via denoising diffusion model. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Vancouver, BC, Canada."},{"key":"ref_40","doi-asserted-by":"crossref","unstructured":"Wu, Z., Chen, X., Xie, S., Shen, J., and Zeng, Y. (2023). Super-resolution of brain MRI images based on denoising diffusion probabilistic model. Biomed. Signal Process. Control, 85.","DOI":"10.1016\/j.bspc.2023.104901"},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"8906","DOI":"10.1109\/TMM.2023.3243616","article-title":"Dilateformer: Multi-scale dilated transformer for visual recognition","volume":"25","author":"Jiao","year":"2023","journal-title":"IEEE Trans. Multimed."},{"key":"ref_42","unstructured":"Zhang, X., Liu, C., Yang, D., Song, T., Ye, Y., Li, K., and Song, Y. (2023). RFAConv: Innovating spatial attention and standard convolutional operation. arXiv."},{"key":"ref_43","doi-asserted-by":"crossref","unstructured":"Liu, W., Lu, H., Fu, H., and Cao, Z. (2023, January 1\u20136). Learning to upsample by learning to sample. Proceedings of the IEEE\/CVF International Conference on Computer Vision, Paris, France.","DOI":"10.1109\/ICCV51070.2023.00554"},{"key":"ref_44","unstructured":"Sohl-Dickstein, J., Weiss, E., Maheswaranathan, N., and Ganguli, S. (2015, January 6\u201311). Deep unsupervised learning using nonequilibrium thermodynamics. Proceedings of the International Conference on Machine Learning, PMLR, Lille, France."},{"key":"ref_45","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_46","unstructured":"Nichol, A.Q., and Dhariwal, P. (2021, January 18\u201324). Improved denoising diffusion probabilistic models. Proceedings of the International Conference on Machine Learning, PMLR, Virtual."},{"key":"ref_47","unstructured":"Li, C., Li, L., Jiang, H., Weng, K., Geng, Y., Li, L., Ke, Z., Li, Q., Cheng, M., and Nie, W. (2022). YOLOv6: A single-stage object detection framework for industrial applications. arXiv."},{"key":"ref_48","first-page":"107984","article-title":"Yolov10: Real-time end-to-end object detection","volume":"37","author":"Wang","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."}],"container-title":["Symmetry"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2073-8994\/17\/5\/674\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T17:23:28Z","timestamp":1760030608000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2073-8994\/17\/5\/674"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,28]]},"references-count":48,"journal-issue":{"issue":"5","published-online":{"date-parts":[[2025,5]]}},"alternative-id":["sym17050674"],"URL":"https:\/\/doi.org\/10.3390\/sym17050674","relation":{},"ISSN":["2073-8994"],"issn-type":[{"value":"2073-8994","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,4,28]]}}}