{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,20]],"date-time":"2026-07-20T13:50:05Z","timestamp":1784555405015,"version":"3.55.0"},"reference-count":59,"publisher":"MDPI AG","issue":"10","license":[{"start":{"date-parts":[[2025,10,5]],"date-time":"2025-10-05T00:00:00Z","timestamp":1759622400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100005022","name":"Beijing Jiaotong University","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100005022","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["www.mdpi.com"],"crossmark-restriction":true},"short-container-title":["Symmetry"],"abstract":"<jats:p>Road-surface distress poses a serious threat to traffic safety and imposes a growing burden on urban maintenance budgets. While modern detectors based on convolutional networks and Vision Transformers achieve strong frame-level performance, they often overlook an essential property of road environments\u2014structural symmetry within road networks and damage patterns. We present Graph-MambaRoadDet (GMRD), a symmetry-aware and lightweight framework that integrates dynamic graph reasoning with state\u2013space modeling for accurate, topology-informed, and real-time road damage detection. Specifically, GMRD employs an EfficientViM-T1 backbone and two DefMamba blocks, whose deformable scanning paths capture sub-pixel crack patterns while preserving geometric symmetry. A superpixel-based graph is constructed by projecting image regions onto OpenStreetMap road segments, encoding both spatial structure and symmetric topological layout. We introduce a Graph-Generating State\u2013Space Model (GG-SSM) that synthesizes sparse sample-specific adjacency in O(M) time, further refined by a fusion module that combines detector self-attention with prior symmetry constraints. A consistency loss promotes smooth predictions across symmetric or adjacent segments. The full INT8 model contains only 1.8 M parameters and 1.5 GFLOPs, sustaining 45 FPS at 7 W on a Jetson Orin Nano\u2014eight times lighter and 1.7\u00d7 faster than YOLOv8-s. On RDD2022, TD-RD, and RoadBench-100K, GMRD surpasses strong baselines by up to +6.1 mAP50:95 and, on the new RoadGraph-RDD benchmark, achieves +5.3 G-mAP and +0.05 consistency gain. Qualitative results demonstrate robustness under shadows, reflections, back-lighting, and occlusion. By explicitly modeling spatial and topological symmetry, GMRD offers a principled solution for city-scale road infrastructure monitoring under real-time and edge-computing constraints.<\/jats:p>","DOI":"10.3390\/sym17101654","type":"journal-article","created":{"date-parts":[[2025,10,6]],"date-time":"2025-10-06T08:10:51Z","timestamp":1759738251000},"page":"1654","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Graph-MambaRoadDet: A Symmetry-Aware Dynamic Graph Framework for Road Damage Detection"],"prefix":"10.3390","volume":"17","author":[{"given":"Zichun","family":"Tian","sequence":"first","affiliation":[{"name":"School of Computer Science and Technology, Beijing Jiaotong University, No. 3 Shangyuan Village, Xizhimenwai, Haidian District, Beijing 100044, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaokang","family":"Shao","sequence":"additional","affiliation":[{"name":"College of Computer and Information Technology, Cangzhou University of Transportation, Xueyuan West Road, Huanghua 061199, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0908-6499","authenticated-orcid":false,"given":"Yuqi","family":"Bai","sequence":"additional","affiliation":[{"name":"School of Environment, Education and Development, The University of Manchester, Manchester M13 9PL, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2025,10,5]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"1621","DOI":"10.1007\/s40996-021-00671-2","article-title":"Concrete road crack detection using deep learning-based faster R-CNN method","volume":"46","year":"2022","journal-title":"Iran. J. Sci. Technol. Trans. Civ. Eng."},{"key":"ref_2","unstructured":"Maeda, H., Sekimoto, Y., Seto, T., Kashiyama, T., and Omata, H. (2018). Road damage detection using deep neural networks with images captured through a smartphone. arXiv."},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Wang, N., Shang, L., and Song, X. (2023). A transformer-optimized deep learning network for road damage detection and tracking. Sensors, 23.","DOI":"10.3390\/s23177395"},{"key":"ref_4","first-page":"460","article-title":"Graph convolutional networks for road networks","volume":"23","author":"Jepsen","year":"2019","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Lebaku, P.K.R., Gao, L., Lu, P., and Sun, J. (2024). Deep learning for pavement condition evaluation using satellite imagery. Infrastructures, 9.","DOI":"10.3390\/infrastructures9090155"},{"key":"ref_6","unstructured":"Bochkovskiy, A., Wang, C.Y., and Liao, H.Y.M. (2020). Yolov4: Optimal speed and accuracy of object detection. arXiv."},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Kirillov, A., Mintun, E., Ravi, N., Mao, H., Rolland, C., Gustafson, L., Xiao, T., Whitehead, S., Berg, A.C., and Lo, W.Y. (2023, January 1\u20136). Segment anything. Proceedings of the IEEE\/CVF International Conference on Computer Vision, Paris, France.","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref_8","unstructured":"Hamilton, W.L., Ying, R., and Leskovec, J. (2017, January 4\u20139). Inductive Representation Learning on Large Graphs. Proceedings of the Advances in Neural Information Processing Systems (NeurIPS), Long Beach, CA, USA."},{"key":"ref_9","unstructured":"Veli\u010dkovi\u0107, P., Cucurull, G., Casanova, A., Romero, A., Li\u00f2, P., and Bengio, Y. (May, January 30). Graph Attention Networks. Proceedings of the International Conference on Learning Representations (ICLR), Vancouver, BC, Canada."},{"key":"ref_10","unstructured":"Gu, A., and Tao, A. (2023). Mamba: Linear-time sequence modeling with selective state spaces. arXiv."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Zubic, N., and Scaramuzza, D. (2025, January 11\u201315). Gg-ssms: Graph-generating state space models. Proceedings of the Computer Vision and Pattern Recognition Conference, Nashville, TN, USA.","DOI":"10.1109\/CVPR52734.2025.02688"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Liu, L., Zhang, M., Yin, J., Liu, T., Ji, W., Piao, Y., and Lu, H. (2025, January 11\u201315). Defmamba: Deformable visual state space model. Proceedings of the Computer Vision and Pattern Recognition Conference, Nashville, TN, USA.","DOI":"10.1109\/CVPR52734.2025.00826"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"109","DOI":"10.1145\/3568678","article-title":"Multi-scale edge-guided learning for 3d reconstruction","volume":"19","author":"Li","year":"2023","journal-title":"ACM Trans. Multimed. Comput. Commun. Appl."},{"key":"ref_14","first-page":"966","article-title":"Pothole detection in asphalt pavement images","volume":"29","author":"Koch","year":"2015","journal-title":"Adv. Eng. Inform."},{"key":"ref_15","unstructured":"Fan, Z., Wu, Y., Lu, J., and Li, W. (2018). Automatic pavement crack detection based on structured prediction with the convolutional neural network. arXiv."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Chen, G.H., Ni, J., Chen, Z., Huang, H., Sun, Y.L., Ip, W.H., and Yung, K.L. (2022). Detection of highway pavement damage based on a CNN using grayscale and HOG features. Sensors, 22.","DOI":"10.3390\/s22072455"},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Safyari, Y., Mahdianpari, M., and Shiri, H. (2024). A review of vision-based pothole detection methods using computer vision and machine learning. Sensors, 24.","DOI":"10.3390\/s24175652"},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Zhang, J., Xia, H., Li, P., Zhang, K., Hong, W., and Guo, R. (2024). A Pavement Crack Detection Method via Deep Learning and a Binocular-Vision-Based Unmanned Aerial Vehicle. Appl. Sci., 14.","DOI":"10.3390\/app14051778"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Li, K., Xu, W., and Yang, L. (2021). Deformation characteristics of raising, widening of old roadway on soft soil foundation. Symmetry, 13.","DOI":"10.3390\/sym13112117"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Fan, L., and Zou, J. (2023). A Novel Road Crack Detection Technology Based on Deep Dictionary Learning and Encoding Networks. Appl. Sci., 13.","DOI":"10.3390\/app132212299"},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Hamishebahar, Y., Guan, H., So, S., and Jo, J. (2022). A Comprehensive Review of Deep Learning-Based Crack Detection Approaches. Appl. Sci., 12.","DOI":"10.3390\/app12031374"},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Ahmed, K.R. (2021). Smart Pothole Detection Using Deep Learning Based on Dilated Convolution. Sensors, 21.","DOI":"10.3390\/s21248406"},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Li, Y., Chen, J., Feng, X., Wang, X., and Zhang, L. (2024). A Pavement Crack Detection and Evaluation Framework for a UAV-Based Inspection System. Appl. Sci., 14.","DOI":"10.20944\/preprints202401.1925.v1"},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Liu, S.S., Budiwirawan, A., Arifin, M.F.A., Chen, W.T., and Huang, Y.H. (2021). Optimization model for the pavement pothole repair problem considering consumable resources. Symmetry, 13.","DOI":"10.3390\/sym13030364"},{"key":"ref_25","first-page":"5613","article-title":"MGD-YOLO: An Enhanced Road Defect Detection Algorithm Based on Multi-Scale Attention Feature Fusion","volume":"84","author":"Li","year":"2025","journal-title":"Comput. Mater. Contin."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"1498","DOI":"10.1109\/TIP.2018.2878966","article-title":"DeepCrack: Learning Hierarchical Convolutional Features for Crack Detection","volume":"28","author":"Zou","year":"2019","journal-title":"IEEE Trans. Image Process."},{"key":"ref_27","unstructured":"Zhu, G., Fan, Z., Liu, J., Yuan, D., Ma, P., Wang, M., Sheng, W., and Wang, K.C. (2022). RHA-Net: An Encoder-Decoder Network with Residual Blocks and Hybrid Attention Mechanisms for Pavement Crack Segmentation. arXiv."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"2025","DOI":"10.1109\/TITS.2018.2856928","article-title":"Automatic pavement crack detection by multi-scale image fusion","volume":"20","author":"Li","year":"2018","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"2910","DOI":"10.1177\/14759217221140976","article-title":"U2CrackNet: A deeper architecture with two-level nested U-structure for pavement crack detection","volume":"22","author":"Shi","year":"2023","journal-title":"Struct. Health Monit."},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Liu, H., Miao, X., Mertz, C., Xu, C., and Kong, H. (2021, January 11\u201317). Crackformer: Transformer network for fine-grained crack detection. Proceedings of the IEEE\/CVF International Conference on Computer Vision, Montreal, BC, Canada.","DOI":"10.1109\/ICCV48922.2021.00376"},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"104297","DOI":"10.1016\/j.dsp.2023.104297","article-title":"SwinCrack: Pavement crack detection using convolutional swin-transformer network","volume":"145","author":"Wang","year":"2024","journal-title":"Digit. Signal Process."},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Tang, Z., Chamchong, R., and Pawara, P. (2023, January 9\u201311). A comparison of road damage detection based on YOLOv8. Proceedings of the 2023 International Conference on Machine Learning and Cybernetics (ICMLC), Adelaide, Australia.","DOI":"10.1109\/ICMLC58545.2023.10327993"},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Park, J., Min, K., Kim, H., Lee, W., Cho, G., and Huh, K. (2018). Road surface classification using a deep ensemble network with sensor feature selection. Sensors, 18.","DOI":"10.3390\/s18124342"},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Kailkhura, V., Aravindh, S., Jha, S.S., and Jayanthi, N. (2020, January 15\u201317). Ensemble learning-based approach for crack detection using CNN. Proceedings of the 2020 4th International Conference on Trends in Electronics and Informatics (ICOEI) (48184), Tirunelveli, India.","DOI":"10.1109\/ICOEI48184.2020.9143035"},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Huang, R., Pedoeem, J., and Chen, C. (2018, January 10\u201313). YOLO-LITE: A real-time object detection algorithm optimized for non-GPU computers. Proceedings of the 2018 IEEE International Conference on Big Data (Big Data), Seattle, WA, USA.","DOI":"10.1109\/BigData.2018.8621865"},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"6012605","DOI":"10.1109\/LGRS.2024.3430900","article-title":"Road-SAM: Adapting the segment anything model to road extraction from large very-high-resolution optical remote sensing images","volume":"21","author":"Feng","year":"2024","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"ref_37","unstructured":"Oquab, M., Darcet, T., Moutakanni, T., Vo, H., Szafraniec, M., Khalidov, V., Fernandez, P., Haziza, D., Massa, F., and El-Nouby, A. (2023). Dinov2: Learning robust visual features without supervision. arXiv."},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"Wang, B., Lin, Y., Guo, S., and Wan, H. (2021, January 2\u20139). GSNet: Learning spatial-temporal correlations from geographical and semantic aspects for traffic accident risk forecasting. Proceedings of the AAAI Conference on Artificial Intelligence, Virtual.","DOI":"10.1609\/aaai.v35i5.16566"},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Yuan, T., Cao, W., Zhang, S., Yang, K., Schoen, M., and Duraisamy, B. (November, January 29). Lane detection and estimation from surround view camera sensing systems. Proceedings of the 2023 IEEE Sensors, Vienna, Austria.","DOI":"10.1109\/SENSORS56945.2023.10324877"},{"key":"ref_40","doi-asserted-by":"crossref","unstructured":"Brust, C.A., Sickert, S., Simon, M., Rodner, E., and Denzler, J. (2015). Convolutional patch networks with spatial prior for road detection and urban scene understanding. arXiv.","DOI":"10.5220\/0005355105100517"},{"key":"ref_41","doi-asserted-by":"crossref","unstructured":"Xiao, X., Li, Z., Wang, W., Xie, J., Lin, H., Roy, S.K., Wang, T., and Xu, M. (2025). TD-RD: A Top-Down Benchmark with Real-Time Framework for Road Damage Detection. arXiv.","DOI":"10.1109\/ICASSP49660.2025.10888616"},{"key":"ref_42","doi-asserted-by":"crossref","unstructured":"Li, Z., Xie, Y., Xiao, X., Tao, L., Liu, J., and Wang, K. (2022, January 19\u201321). An Image Data Augmentation Algorithm Based on YOLOv5s-DA for Pavement Distress Detection. Proceedings of the 2022 5th International Conference on Pattern Recognition and Artificial Intelligence (PRAI), Chengdu, China.","DOI":"10.1109\/PRAI55851.2022.9904187"},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"109670","DOI":"10.1016\/j.patcog.2023.109670","article-title":"A decomposition dynamic graph convolutional recurrent network for traffic forecasting","volume":"142","author":"Weng","year":"2023","journal-title":"Pattern Recognit."},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"101946","DOI":"10.1016\/j.inffus.2023.101946","article-title":"Generic dynamic graph convolutional network for traffic flow forecasting","volume":"100","author":"Xu","year":"2023","journal-title":"Inf. Fusion"},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"111820","DOI":"10.1109\/ACCESS.2022.3211306","article-title":"Graph anomaly detection with graph neural networks: Current status and challenges","volume":"10","author":"Kim","year":"2022","journal-title":"IEEE Access"},{"key":"ref_46","doi-asserted-by":"crossref","unstructured":"Pham, T.V., Tran, N.N.Q., Pham, H.M., Nguyen, T.M., and Ta Minh, T. (2020, January 13\u201315). Efficient low-latency dynamic licensing for deep neural network deployment on edge devices. Proceedings of the 3rd International Conference on Computational Intelligence and Intelligent Systems, Tokyo, Japan.","DOI":"10.1145\/3440840.3440860"},{"key":"ref_47","unstructured":"Gu, A., Goel, K., and R\u00e9, C. (2021). Efficiently modeling long sequences with structured state spaces. arXiv."},{"key":"ref_48","unstructured":"Zhu, L., Liao, B., Zhang, Q., Wang, X., Liu, W., and Wang, X. (2024). Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model. arXiv."},{"key":"ref_49","doi-asserted-by":"crossref","unstructured":"Li, K., Li, X., Wang, Y., He, Y., Wang, Y., Wang, L., and Qiao, Y. (October, January 29). VideoMamba: State Space Model for Efficient Video Understanding. Proceedings of the Computer Vision\u2014ECCV 2024: 18th European Conference, Milan, Italy.","DOI":"10.1007\/978-3-031-73347-5_14"},{"key":"ref_50","doi-asserted-by":"crossref","unstructured":"Lee, S., Choi, J., and Kim, H.J. (2025, January 11\u201315). EfficientViM: Efficient Vision Mamba with Hidden-State Mixer based State Space Duality. Proceedings of the IEEE\/CVF Computer Vision and Pattern Recognition Conference (CVPR), Nashville, TN, USA.","DOI":"10.1109\/CVPR52734.2025.01390"},{"key":"ref_51","doi-asserted-by":"crossref","first-page":"5370","DOI":"10.1109\/TPAMI.2022.3214832","article-title":"A systematic survey on deep generative models for graph generation","volume":"45","author":"Guo","year":"2022","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_52","doi-asserted-by":"crossref","unstructured":"Chelliah, P.R., Rahmani, A.M., Colby, R., Nagasubramanian, G., and Ranganath, S. (2024). Model Optimization Methods for Efficient and Edge AI: Federated Learning Architectures, Frameworks and Applications, John Wiley & Sons.","DOI":"10.1002\/9781394219230"},{"key":"ref_53","unstructured":"Miller, J.S., and Bellinger, W.Y. (2003). Distress Identification Manual for the Long-Term Pavement Performance Program, Federal Highway Administration."},{"key":"ref_54","unstructured":"(2009). Standard Practice for Roads and Parking Lots Pavement Condition Index Surveys (Standard No. ASTM-D6433)."},{"key":"ref_55","doi-asserted-by":"crossref","unstructured":"Arya, D., Maeda, H., Ghosh, S.K., Toshniwal, D., and Sekimoto, Y. (2022). RDD2022: A Multi-National Image Dataset for Automatic Road Damage Detection. arXiv.","DOI":"10.1016\/j.dib.2021.107133"},{"key":"ref_56","doi-asserted-by":"crossref","first-page":"3434","DOI":"10.1109\/TITS.2016.2552248","article-title":"Automatic Road Crack Detection Using Random Structured Forests","volume":"17","author":"Shi","year":"2016","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"ref_57","unstructured":"Xiao, X., Zhang, Y., Wang, J., Zhao, L., Wei, Y., Li, H., Li, Y., Wang, X., Roy, S.K., and Xu, H. (2025). RoadBench: A Vision-Language Foundation Model and Benchmark for Road Damage Understanding. arXiv."},{"key":"ref_58","unstructured":"Howard, A.G., Zhu, M., Chen, B., Kalenichenko, D., Wang, W., Weyand, T., Andreetto, M., and Adam, H. (2017). MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications. arXiv."},{"key":"ref_59","doi-asserted-by":"crossref","unstructured":"Tan, M., Pang, R., and Le, Q.V. (2020, January 13\u201319). EfficientDet: Scalable and Efficient Object Detection. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA.","DOI":"10.1109\/CVPR42600.2020.01079"}],"container-title":["Symmetry"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2073-8994\/17\/10\/1654\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,7]],"date-time":"2025-10-07T04:13:56Z","timestamp":1759810436000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2073-8994\/17\/10\/1654"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,5]]},"references-count":59,"journal-issue":{"issue":"10","published-online":{"date-parts":[[2025,10]]}},"alternative-id":["sym17101654"],"URL":"https:\/\/doi.org\/10.3390\/sym17101654","relation":{},"ISSN":["2073-8994"],"issn-type":[{"value":"2073-8994","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,5]]}}}