{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,2]],"date-time":"2026-09-02T11:17:35Z","timestamp":1788347855838,"version":"build-2803163510"},"reference-count":50,"publisher":"MDPI AG","issue":"17","license":[{"start":{"date-parts":[[2026,9,2]],"date-time":"2026-09-02T00:00:00Z","timestamp":1788307200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Ministry of Land, Infrastructure and Transport, Republic of Korea"},{"id":[{"id":"https:\/\/ror.org\/04xt5aa77","id-type":"ROR","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Vehicle-mounted vision sensing, in which cameras on patrol vehicles acquire ground-level imagery across a road network, offers a low-cost, scalable approach to large-scale road surface monitoring and pothole detection. However, its real-world effectiveness depends not only on detector accuracy on curated imagery but also on two rarely reported factors: field acquisition conditions and pipeline architecture. We present a multi-year field study of a vehicle-based pothole-monitoring system. First, controlled field comparisons show how acquisition geometry and device thermal behavior affect detection yield: across three vehicle types, an actively cooled windshield mount achieved yields of 41.7\u201358.3%, versus 0\u20134.2% for a rear-view-mirror baseline. Second, we identify a shared-bias limitation in a homogeneous two-stage detector cascade, in which a second You Only Look Once (YOLO) detector reproduces rather than eliminates first-stage false positives. Third, we redesign the pipeline as a heterogeneous detection-to-classification cascade: an edge-deployed YOLOv12-large detector proposes candidate regions, and a server-side EfficientNet-B2 classifier verifies each. On field data, this raised the detection mean average precision (mAP) from 32.7% to 69.5% and reduced the false-positive rate from 99.96% to 32.26%, cutting manual inspection workload by about 70%. Unlike prior work that mainly optimizes detector architectures, this study shows that acquisition geometry and heterogeneous verification dominate real-world sensing performance under operational deployment.<\/jats:p>","DOI":"10.3390\/s26175573","type":"journal-article","created":{"date-parts":[[2026,9,2]],"date-time":"2026-09-02T10:57:23Z","timestamp":1788346643000},"page":"5573","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Vehicle-Mounted Vision Sensing for Large-Scale Road Surface Monitoring: A Multi-Year Field Study of Acquisition Geometry and a Heterogeneous Detection\u2013Classification Pipeline for Pothole Mapping"],"prefix":"10.3390","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2543-6981","authenticated-orcid":false,"given":"Moon-Sup","family":"Lee","sequence":"first","affiliation":[{"name":"Korea Institute of Civil Engineering and Building Technology, Goyang-si 10223, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"conceptualization","vocabulary":"credit"},{"role":"methodology","vocabulary":"credit"},{"role":"software","vocabulary":"credit"},{"role":"validation","vocabulary":"credit"},{"role":"formal-analysis","vocabulary":"credit"},{"role":"investigation","vocabulary":"credit"},{"role":"data-curation","vocabulary":"credit"},{"role":"writing-original-draft","vocabulary":"credit"},{"role":"visualization","vocabulary":"credit"}]},{"given":"Seung-Yeon","family":"Han","sequence":"additional","affiliation":[{"name":"Korea Institute of Civil Engineering and Building Technology, Goyang-si 10223, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"conceptualization","vocabulary":"credit"},{"role":"visualization","vocabulary":"credit"},{"role":"writing-review-editing","vocabulary":"credit"},{"role":"supervision","vocabulary":"credit"},{"role":"project-administration","vocabulary":"credit"},{"role":"funding-acquisition","vocabulary":"credit"}]}],"member":"1968","published-online":{"date-parts":[[2026,9,2]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Redmon, J., Divvala, S., Girshick, R., and Farhadi, A. (2016, January 27\u201330). You Only Look Once: Unified, Real-Time Object Detection. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.91"},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Wang, C.-Y., Bochkovskiy, A., and Liao, H.-Y.M. (2023, January 17\u201324). YOLOv7: Trainable Bag-of-Freebies Sets New State-of-the-Art for Real-Time Object Detectors. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Vancouver, BC, Canada.","DOI":"10.1109\/CVPR52729.2023.00721"},{"key":"ref_3","first-page":"846","article-title":"RDD2022: A Multi-National Image Dataset for Automatic Road Damage Detection","volume":"11","author":"Arya","year":"2024","journal-title":"Geosci. Data J."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"103935","DOI":"10.1016\/j.autcon.2021.103935","article-title":"Deep Learning-Based Road Damage Detection and Classification for Multiple Countries","volume":"132","author":"Arya","year":"2021","journal-title":"Autom. Constr."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"1127","DOI":"10.1111\/mice.12387","article-title":"Road Damage Detection and Classification Using Deep Neural Networks with Smartphone Images","volume":"33","author":"Maeda","year":"2018","journal-title":"Comput.-Aided Civ. Infrastruct. Eng."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"2127","DOI":"10.1016\/j.measurement.2013.03.006","article-title":"Review of Mobile Mapping and Surveying Technologies","volume":"46","author":"Puente","year":"2013","journal-title":"Measurement"},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Chiang, K.-W., Tsai, G.-J., and Zeng, J.-C. (2021). Mobile Mapping Technologies. Urban Informatics, Springer.","DOI":"10.1007\/978-981-15-8983-6_25"},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Eriksson, J., Girod, L., Hull, B., Newton, R., Madden, S., and Balakrishnan, H. (2008, January 17\u201320). The Pothole Patrol: Using a Mobile Sensor Network for Road Surface Monitoring. Proceedings of the 6th International Conference on Mobile Systems, Applications, and Services (MobiSys), Breckenridge, CO, USA.","DOI":"10.1145\/1378600.1378605"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"81","DOI":"10.1504\/IJSNET.2021.118485","article-title":"A Survey on State-of-the-Art Road Surface Monitoring Techniques for Intelligent Transportation Systems","volume":"37","author":"Chhabra","year":"2021","journal-title":"Int. J. Sens. Netw."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"3397","DOI":"10.3390\/eng5040177","article-title":"A Comprehensive Review of Smartphone and Other Device-Based Techniques for Road Surface Monitoring","volume":"5","author":"Alqaydi","year":"2024","journal-title":"Eng"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"1411","DOI":"10.1038\/s41597-025-05471-1","article-title":"Multimodal Sensor Dataset from a Vehicle-Mounted Mobile Mapping System for Comprehensive Urban Scenes","volume":"12","author":"Lu","year":"2025","journal-title":"Sci. Data"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Samadzadegan, F., Dadrass Javan, F., Ashtari Mahini, F., Gholamshahi, M., and Nex, F. (2024). Automatic Road Pavement Distress Recognition Using Deep Learning Networks from Unmanned Aerial Imagery. Drones, 8.","DOI":"10.3390\/drones8060244"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"16","DOI":"10.1007\/s41062-023-01315-2","article-title":"Smart Monitoring of Road Pavement Deformations from UAV Images by Using Machine Learning","volume":"9","author":"Ibrahim","year":"2024","journal-title":"Innov. Infrastruct. Solut."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"931","DOI":"10.3390\/vehicles5030051","article-title":"Road Condition Monitoring Using Vehicle Built-in Cameras and GPS Sensors: A Deep Learning Approach","volume":"5","author":"Ruseruka","year":"2023","journal-title":"Vehicles"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"914","DOI":"10.1080\/14680629.2023.2237601","article-title":"A Review on Pavement Data Acquisition and Analytics Tools Using Autonomous Vehicles","volume":"25","author":"Sholevar","year":"2024","journal-title":"Road Mater. Pavement Des."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"4212","DOI":"10.1038\/s41467-025-59516-5","article-title":"Lightweight deep learning for real-time road distress detection on mobile devices","volume":"16","author":"Hu","year":"2025","journal-title":"Nat. Commun."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Bhatia, V., Pathak, A.K., Singh, A.K., Raghuwanshi, S., Kumar, P., and Krejcar, O. (Int. J. Transp. Sci. Technol., 2026). Real-time pothole detection using YOLO models: An efficient and cost-effective solution for infrastructure monitoring, Int. J. Transp. Sci. Technol., in press.","DOI":"10.1016\/j.ijtst.2025.12.004"},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Ferrari, E., Meyer, J., and Nebiker, S. (2026). AI-Based Automated Visual Condition Assessment of Municipal Road Infrastructure Using High-Resolution 3D Street-Level Imagery. Infrastructures, 11.","DOI":"10.3390\/infrastructures11030090"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Ronneberger, O., Fischer, P., and Brox, T. (2015). U-Net: Convolutional Networks for Biomedical Image Segmentation. Medical Image Computing and Computer-Assisted Intervention\u2014MICCAI 2015, Springer.","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"57298","DOI":"10.1109\/ACCESS.2020.2982220","article-title":"A Review on Negative Road Anomaly Detection Methods","volume":"8","author":"Dib","year":"2020","journal-title":"IEEE Access"},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Kim, Y.-M., Kim, Y.-G., Son, S.-Y., Lim, S.-Y., Choi, B.-Y., and Choi, D.-H. (2022). Review of Recent Automated Pothole-Detection Methods. Appl. Sci., 12.","DOI":"10.3390\/app12115320"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"24802","DOI":"10.1109\/JSEN.2024.3399008","article-title":"POT-YOLO: Real-Time Road Pothole Detection Using Edge Segmentation-Based YOLOv8 Network","volume":"24","author":"Bhavana","year":"2024","journal-title":"IEEE Sens. J."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"17649","DOI":"10.1109\/JIOT.2025.3537640","article-title":"Real-Time Road Damage Detection Using an Optimized YOLOv9s-Fusion in IoT Infrastructure","volume":"12","author":"Khan","year":"2025","journal-title":"IEEE Internet Things J."},{"key":"ref_24","first-page":"100547","article-title":"Augmenting Roadway Safety with Machine Learning and Deep Learning: Pothole Detection and Dimension Estimation Using In-Vehicle Technologies","volume":"16","author":"Ruseruka","year":"2024","journal-title":"Mach. Learn. Appl."},{"key":"ref_25","first-page":"100668","article-title":"Enhancing Road Safety: A Convolutional Neural Network-Based Approach for Road Damage Detection","volume":"20","author":"Bouhsissin","year":"2025","journal-title":"Mach. Learn. Appl."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"e2519","DOI":"10.7717\/peerj-cs.2519","article-title":"Modified MobileNetV2 Transfer Learning Model to Detect Road Potholes","volume":"11","author":"Tanwar","year":"2025","journal-title":"PeerJ Comput. Sci."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"184541","DOI":"10.1109\/ACCESS.2024.3512783","article-title":"Deep Learning Enhanced Feature Extraction of Potholes Using Vision and LiDAR Data for Road Maintenance","volume":"12","author":"Karukayil","year":"2024","journal-title":"IEEE Access"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"137","DOI":"10.1007\/s11554-025-01683-1","article-title":"Advancements in Real-Time Road Damage Detection: A Comprehensive Survey of Methodologies and Datasets","volume":"22","author":"Abdelwahed","year":"2025","journal-title":"J. Real-Time Image Process."},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., and Sun, J. (2016, January 27\u201330). Deep Residual Learning for Image Recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., and Wojna, Z. (2016, January 27\u201330). Rethinking the Inception Architecture for Computer Vision. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"21","DOI":"10.1007\/978-3-319-46448-0_2","article-title":"SSD: Single Shot MultiBox Detector","volume":"Volume 9905","author":"Liu","year":"2016","journal-title":"Computer Vision\u2014ECCV 2016"},{"key":"ref_32","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":"2017","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Lin, T.-Y., Goyal, P., Girshick, R., He, K., and Doll\u00e1r, P. (2017, January 22\u201329). Focal Loss for Dense Object Detection. Proceedings of the IEEE International Conference on Computer Vision (ICCV), Venice, Italy.","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., and Zagoruyko, S. (2020). End-to-End Object Detection with Transformers. Computer Vision\u2014ECCV 2020, Springer.","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Zhao, Y., Lv, W., Xu, S., Wei, J., Wang, G., Dang, Q., Liu, Y., and Chen, J. (2024, January 17\u201321). DETRs Beat YOLOs on Real-Time Object Detection (RT-DETR). Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA.","DOI":"10.1109\/CVPR52733.2024.01605"},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Wang, C.-Y., Yeh, I.-H., and Liao, H.-Y.M. (2024). YOLOv9: Learning What You Want to Learn Using Programmable Gradient Information. arXiv.","DOI":"10.1007\/978-3-031-72751-1_1"},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Wang, A., Chen, H., Liu, L., Chen, K., Lin, Z., Han, J., and Ding, G. (2024, January 10\u201315). YOLOv10: Real-Time End-to-End Object Detection. Proceedings of the Advances in Neural Information Processing Systems (NeurIPS), Vancouver, BC, Canada.","DOI":"10.52202\/079017-3429"},{"key":"ref_38","unstructured":"Khanam, R., and Hussain, M. (2024). YOLOv11: An Overview of the Key Architectural Enhancements. arXiv."},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Tian, Y., Ye, Q., and Doermann, D. (2025). YOLOv12: Attention-Centric Real-Time Object Detectors. arXiv.","DOI":"10.52202\/085713-2627"},{"key":"ref_40","doi-asserted-by":"crossref","unstructured":"Lin, T.-Y., Doll\u00e1r, P., Girshick, R., He, K., Hariharan, B., and Belongie, S. (2017, January 21\u201326). Feature Pyramid Networks for Object Detection. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA.","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref_41","doi-asserted-by":"crossref","unstructured":"Neubeck, A., and Van Gool, L. (2006, January 20\u201324). Efficient Non-Maximum Suppression. Proceedings of the 18th International Conference on Pattern Recognition (ICPR), Hong Kong, China.","DOI":"10.1109\/ICPR.2006.479"},{"key":"ref_42","unstructured":"Tan, M., and Le, Q. (2019, January 9\u201315). EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks. Proceedings of the 36th International Conference on Machine Learning (ICML), Long Beach, CA, USA."},{"key":"ref_43","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., and Fei-Fei, L. (2009, January 20\u201325). ImageNet: A Large-Scale Hierarchical Image Database. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Miami, FL, USA.","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref_44","unstructured":"(2026, July 01). LiteRT (TensorFlow Lite): On-Device Machine-Learning Runtime. Available online: https:\/\/ai.google.dev\/edge\/litert."},{"key":"ref_45","doi-asserted-by":"crossref","unstructured":"Efron, B., and Tibshirani, R.J. (1994). An Introduction to the Bootstrap, Chapman & Hall\/CRC.","DOI":"10.1201\/9780429246593"},{"key":"ref_46","unstructured":"National Information Society Agency (2026, July 01). AI Hub Road-Obstacle\/Surface-Recognition Dataset. AI Hub, Republic of Korea. Available online: https:\/\/www.aihub.or.kr."},{"key":"ref_47","doi-asserted-by":"crossref","unstructured":"Akiba, T., Sano, S., Yanase, T., Ohta, T., and Koyama, M. (2019, January 4\u20138). Optuna: A Next-Generation Hyperparameter Optimization Framework. Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, Anchorage, AK, USA.","DOI":"10.1145\/3292500.3330701"},{"key":"ref_48","doi-asserted-by":"crossref","unstructured":"Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., and Chen, L.-C. (2018, January 18\u201323). MobileNetV2: Inverted Residuals and Linear Bottlenecks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Salt Lake City, UT, USA.","DOI":"10.1109\/CVPR.2018.00474"},{"key":"ref_49","unstructured":"Howard, A., Sandler, M., Chu, G., Chen, L.-C., Chen, B., Tan, M., Wang, W., Zhu, Y., Pang, R., and Vasudevan, V. (November, January 27). Searching for MobileNetV3. Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), Seoul, Republic of Korea."},{"key":"ref_50","unstructured":"Tan, M., and Le, Q. (2021, January 18\u201324). EfficientNetV2: Smaller Models and Faster Training. Proceedings of the 38th International Conference on Machine Learning (ICML), Virtual."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/17\/5573\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,2]],"date-time":"2026-09-02T11:00:09Z","timestamp":1788346809000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/17\/5573"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,2]]},"references-count":50,"journal-issue":{"issue":"17","published-online":{"date-parts":[[2026,9]]}},"alternative-id":["s26175573"],"URL":"https:\/\/doi.org\/10.3390\/s26175573","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,2]]}}}