{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T13:10:58Z","timestamp":1788268258829,"version":"build-2803163510"},"reference-count":45,"publisher":"MDPI AG","issue":"8","license":[{"start":{"date-parts":[[2026,4,21]],"date-time":"2026-04-21T00:00:00Z","timestamp":1776729600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Vulnerable road users in informal urban environments confront a distinct set of hazards that standard computer vision datasets are ill-equipped to represent: artisanal speed bumps constructed without regulatory compliance, deteriorated road markings, and the mototaxi\u2014a three-wheeled motorized vehicle that constitutes the primary informal transport mode in intermediate Andean cities yet is absent from all major international repositories. This paper presents QHAWAY\u2014from Quechua qhaway, a transitive verb meaning \u201cto look; to observe\u201d\u2014an Advanced Driver Assistance System (ADAS) predicated on instance segmentation, monocular distance estimation via the pinhole camera model, and Time-to-Collision (TTC) computation, developed for the road environment of Ayacucho, Peru (2761 m a.s.l.), a city recognised by UNESCO as a Creative City of Crafts and Folk Art since 2019. A hybrid dataset comprising 25,602 images with 127,525 annotated instances across 12 classes was assembled by combining an original local collection of 4598 images (10,701 instances) captured through four complementary acquisition methods across the five urban districts of the Huamanga province with three established international datasets (BDD100K, BSTLD, RLMD; 21,004 images, 116,824 instances). A three-phase progressive training strategy with monotonically increasing resolution (640, 800, and 1024 pixels) was evaluated as an ablation study. A multi-architecture comparison spanning YOLOv8L-seg and the YOLO26 family (nano, small, large) identified YOLO26L-seg as the best-performing model, attaining mAP50 Box of 0.829 and mAP50 Mask of 0.788 at epoch 179. The integration of ByteTrack multi-object tracking with the pinhole equation D=(Hreal\u00d7f)\/hpx delineates operational risk zones aligned with the NHTSA forward collision warning standard (danger: &lt;3 m; caution: 3\u20137 m; TTC threshold \u2264 2.4 s). The system sustains processing rates of 19.2\u201325.4 FPS on an NVIDIA RTX 5080 GPU. A systematic field survey established that 96% of the audited speed bumps fail to comply with MTC Directive No. 01-2011-MTC\/14, constituting the first quantitative record of informal road infrastructure non-compliance in the Andean region. Validation was conducted under naturalistic driving conditions without staged scenarios. Grad-CAM explainability analysis, encompassing three complementary visualisation algorithms (Grad-CAM, Grad-CAM++, and EigenCAM), confirmed that model attention concentrates consistently on safety-critical objects.<\/jats:p>","DOI":"10.3390\/s26082569","type":"journal-article","created":{"date-parts":[[2026,4,21]],"date-time":"2026-04-21T16:10:44Z","timestamp":1776787844000},"page":"2569","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["QHAWAY: An Instance Segmentation and Monocular Distance Estimation ADAS for Vulnerable Road Users in Informal Andean Urban Corridors"],"prefix":"10.3390","volume":"26","author":[{"given":"Abel De la","family":"Cruz-Moran","sequence":"first","affiliation":[{"name":"Research Group GECOTRAN (Studies in Management, Construction and Transport), Faculty of Mining, Geological and Civil Engineering, Universidad Nacional de San Crist\u00f3bal de Huamanga, Ayacucho 05000, Peru"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3682-7061","authenticated-orcid":false,"given":"Hemerson","family":"Lizarbe-Alarcon","sequence":"additional","affiliation":[{"name":"Research Group GECOTRAN (Studies in Management, Construction and Transport), Faculty of Mining, Geological and Civil Engineering, Universidad Nacional de San Crist\u00f3bal de Huamanga, Ayacucho 05000, Peru"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1648-2361","authenticated-orcid":false,"given":"Wilmer","family":"Moncada","sequence":"additional","affiliation":[{"name":"Remote Sensing and Renewable Energy Laboratory (LABTELER), Faculty of Mining, Geological and Civil Engineering, Universidad Nacional de San Crist\u00f3bal de Huamanga, Ayacucho 05000, Peru"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2962-682X","authenticated-orcid":false,"given":"Victor","family":"Bellido-Aedo","sequence":"additional","affiliation":[{"name":"Research Group GECOTRAN (Studies in Management, Construction and Transport), Faculty of Mining, Geological and Civil Engineering, Universidad Nacional de San Crist\u00f3bal de Huamanga, Ayacucho 05000, Peru"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2393-5311","authenticated-orcid":false,"given":"Carlos","family":"Carrasco-Badajoz","sequence":"additional","affiliation":[{"name":"Biodiversity and Geographic Information Systems Laboratory (BioSIG), Faculty of Mining, Geological and Civil Engineering, Universidad Nacional de San Crist\u00f3bal de Huamanga, Ayacucho 05000, Peru"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8964-5347","authenticated-orcid":false,"given":"Carolina","family":"Rayme-Chalco","sequence":"additional","affiliation":[{"name":"Biodiversity and Geographic Information Systems Laboratory (BioSIG), Faculty of Mining, Geological and Civil Engineering, Universidad Nacional de San Crist\u00f3bal de Huamanga, Ayacucho 05000, Peru"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6890-5370","authenticated-orcid":false,"given":"Cristhian","family":"Aldana","sequence":"additional","affiliation":[{"name":"Research Group on Productive Efficiency, Environment and Society (EPAS UNF), Universidad Nacional de Frontera, Sullana 20100, Peru"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yesenia","family":"Saavedra","sequence":"additional","affiliation":[{"name":"Research Group on Productive Efficiency, Environment and Society (EPAS UNF), Universidad Nacional de Frontera, Sullana 20100, Peru"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-4180-9779","authenticated-orcid":false,"given":"Edwin","family":"Saavedra","sequence":"additional","affiliation":[{"name":"Universidad Nacional de Frontera, Sullana 20100, Peru"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alex","family":"Pereda","sequence":"additional","affiliation":[{"name":"Statistics Programme, Faculty of Mining, Geological and Civil Engineering, Universidad Nacional de San Crist\u00f3bal de Huamanga, Ayacucho 05000, Peru"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,4,21]]},"reference":[{"key":"ref_1","unstructured":"World Health Organization (2023). Global Status Report on Road Safety 2023, WHO."},{"key":"ref_2","unstructured":"World Health Organization (2025, January 18\u201320). Leaders Make New Road Safety Commitments, Endorse New Declaration on Action to Reduce Road Deaths. Proceedings of the 4th Global Ministerial Conference on Road Safety, Marrakech, Morocco."},{"key":"ref_3","first-page":"9","article-title":"Quechua Language Shift, Maintenance, and Revitalization in the Andes: The Case for Language Planning","volume":"167","author":"Hornberger","year":"2004","journal-title":"Int. J. Sociol. Lang."},{"key":"ref_4","unstructured":"Cerr\u00f3n-Palomino, R. (1994). Quechua Sure\u00f1o: Diccionario Unificado, Biblioteca Nacional del Per\u00fa."},{"key":"ref_5","unstructured":"Observatorio Nacional de Seguridad Vial (ONSV) (2024). Estad\u00edsticas de Siniestralidad Vial 2023."},{"key":"ref_6","unstructured":"Observatorio Nacional de Seguridad Vial (ONSV) (2024). Informe de V\u00edctimas Fatales en Siniestros de Tr\u00e1nsito e Identificaci\u00f3n de Puntos de Alta Siniestralidad en la Regi\u00f3n Ayacucho, 2021\u20132024."},{"key":"ref_7","unstructured":"Polic\u00eda Nacional del Per\u00fa (PNP) (2024). Anuario Estad\u00edstico de Accidentes de Tr\u00e1nsito 2023."},{"key":"ref_8","first-page":"3247","article-title":"Intelligent Traffic Light Optimization System Using Convolutional Neural Networks for Historic City Centers in Complex Scenarios","volume":"12","year":"2025","journal-title":"Math. Model. Eng. Probl."},{"key":"ref_9","first-page":"48712","article-title":"A Comprehensive Survey on Advanced Driver Assistance Systems Based on Deep Learning Techniques","volume":"13","author":"Shah","year":"2025","journal-title":"IEEE Access"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"530","DOI":"10.1016\/j.aej.2025.03.077","article-title":"Assessing YOLO Models for Real-Time Object Detection in Urban Environments for Advanced Driver-Assistance Systems","volume":"123","author":"Ayachi","year":"2025","journal-title":"Alex. Eng. J."},{"key":"ref_11","unstructured":"Unar, S., Wang, W., Zhang, C., and Zhang, Y. (2026). Visual Attention Models for Pixel-Level Scene Understanding in Autonomous Driving. Sensors, 26."},{"key":"ref_12","first-page":"218","article-title":"Multi-Task Learning for Simultaneous Monocular Depth Estimation and Object Detection","volume":"13","author":"Dai","year":"2021","journal-title":"IEEE Intell. Transp. Syst. Mag."},{"key":"ref_13","unstructured":"Chaman, A., Iqbal, M., Ul-Hassan, M., and Siddique, A. (2026). Benchmarking YOLO-Based Monocular ADAS for Low-Resource Deployment. Sensors, 26."},{"key":"ref_14","unstructured":"National Highway Traffic Safety Administration (2013). Event Data Recorders and Forward Collision Warning Systems."},{"key":"ref_15","first-page":"153","article-title":"Pedestrian Detection Based on Monocular Camera Using Geometry Constraint","volume":"11","author":"Park","year":"2014","journal-title":"Int. J. Adv. Robot. Syst."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Sun, P., Jiang, Y., Yu, D., Weng, F., Yuan, Z., Luo, P., Liu, W., and Wang, X. (2022). ByteTrack: Multi-Object Tracking by Associating Every Detection Box. European Conference on Computer Vision, Springer.","DOI":"10.1007\/978-3-031-20047-2_1"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"1494","DOI":"10.1016\/j.procs.2025.09.091","article-title":"Traffic Sign Detection Using YOLO: Evaluating Failures on Localized Data","volume":"269","author":"Linardi","year":"2025","journal-title":"Procedia Comput. Sci."},{"key":"ref_18","unstructured":"Du, Z., Li, H., Chen, X., and Wang, M. (2026). ML-E-YOLO: Multi-Label Enhanced YOLO for Heterogeneous Urban Vehicle Detection. Sensors, 26."},{"key":"ref_19","first-page":"18234","article-title":"EMD-YOLOv8: Enhanced Multi-Class Detection for Diverse Vehicle Types","volume":"14","author":"Bao","year":"2026","journal-title":"IEEE Access"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Wang, R., Luo, X., Ye, Q., Jiang, Y., and Liu, W. (2024). Research on Visual Perception of Speed Bumps Based on Lightweight FPNet. Sensors, 24.","DOI":"10.3390\/s24072130"},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Kaya, \u00d6., \u00c7odur, M.Y., and Mustafaraj, E. (2023). Automatic Detection of Pedestrian Crosswalk with Faster R-CNN and YOLOv7. Buildings, 13.","DOI":"10.3390\/buildings13041070"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"e42428","DOI":"10.1016\/j.heliyon.2025.e42428","article-title":"Evaluating Pedestrian Crossing Safety: CNN Model Trained on Paired Aerial and Subjective Perspective Images","volume":"11","author":"Russon","year":"2025","journal-title":"Heliyon"},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Kulawik, J., and Kuczy\u0144ski, \u0141. (2025). AI-Based Detection and Classification of Horizontal Road Markings Dedicated to Driver Assistance Systems. Appl. Sci., 15.","DOI":"10.3390\/app152212189"},{"key":"ref_24","unstructured":"Jocher, G., and Qiu, J. (2026, March 06). Ultralytics YOLO26. Available online: https:\/\/github.com\/ultralytics\/ultralytics\/tree\/main."},{"key":"ref_25","first-page":"3714","article-title":"Pedestrian Detection Based on Instance Segmentation for Autonomous Driving","volume":"25","author":"Pan","year":"2024","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Peralta-L\u00f3pez, J.-E., Morales-Viscaya, J.A., Lazaro-Mata, D., Villasenor-Aguilar, M.J., Prado-Olivarez, J., Perez-Pinal, F.J., Padilla-Medina, J.A., Mart\u00ednez-Nolasco, J.J., and Barranco-Gutierrez, A.I. (2023). Speed Bump and Pothole Detection Using Deep Neural Network with ZED Camera. Appl. Sci., 13.","DOI":"10.3390\/app13148349"},{"key":"ref_27","first-page":"119561","article-title":"An Intelligent Hybrid YOLO\u2013CNN\u2013LSTM Framework for Real-Time Road Infrastructure Monitoring","volume":"242","author":"Zhumadillayeva","year":"2025","journal-title":"Measurement"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"100563","DOI":"10.1016\/j.array.2025.100563","article-title":"Urban Road Pedestrian Detection System Integrating IoT Technology and Multi-Sensor Data Fusion","volume":"28","author":"Han","year":"2025","journal-title":"Array"},{"key":"ref_29","first-page":"10717","article-title":"CDNet: A Real-Time and Robust Crosswalk Detection Network on Jetson Nano Based on YOLOv5","volume":"34","author":"Zhang","year":"2022","journal-title":"Neural Comput. Appl."},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Wang, G., Lin, T., Dong, X., Wang, L., Leng, Q., and Shin, S.Y. (2024). CGADNet: A Lightweight, Real-Time Crosswalk and Guide Arrow Detection Network for Complex Scenes. Appl. Sci., 14.","DOI":"10.3390\/app14209445"},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"234","DOI":"10.1038\/s41586-020-2302-0","article-title":"A Positively Selected FBN1 Missense Variant Reduces Height in Peruvian Individuals","volume":"582","author":"Asgari","year":"2020","journal-title":"Nature"},{"key":"ref_32","unstructured":"Microsoft Corporation (2026, March 06). Edge TTS: Text-to-Speech via Microsoft Azure Neural Voices. Available online: https:\/\/github.com\/rany2\/edge-tts."},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Yu, F., Chen, H., Wang, X., Xian, W., Chen, Y., Liu, F., Madhavan, V., and Darrell, T. (2020). BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learning. Proceedings of the IEEE\/CVF CVPR, IEEE.","DOI":"10.1109\/CVPR42600.2020.00271"},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Behrendt, K., Novak, L., and Botros, R. (2017). A Deep Learning Approach to Traffic Lights: Detection, Tracking, and Classification. Proceedings of the IEEE ICRA, IEEE.","DOI":"10.1109\/ICRA.2017.7989163"},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"41","DOI":"10.1109\/TVT.2019.2949603","article-title":"Robust Lane Detection from Continuous Driving Scenes Using Deep Neural Networks","volume":"69","author":"Zou","year":"2020","journal-title":"IEEE Trans. Veh. Technol."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"157","DOI":"10.1007\/s11263-007-0090-8","article-title":"LabelMe: A Database and Web-Based Tool for Image Annotation","volume":"77","author":"Russell","year":"2008","journal-title":"Int. J. Comput. Vis."},{"key":"ref_37","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. (2023). Segment Anything. Proceedings of the IEEE\/CVF ICCV, IEEE.","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref_38","unstructured":"Ravi, N., Gabeur, V., Hu, Y.-T., Hu, R., Ryali, C., Ma, T., Khedr, H., R\u00e4dle, R., Rolland, C., and Gustafson, L. (2024). SAM 2: Segment Anything in Images and Videos. arXiv."},{"key":"ref_39","unstructured":"Jocher, G., Chaurasia, A., and Qiu, J. (2026, March 06). Ultralytics YOLOv8. Available online: https:\/\/github.com\/ultralytics\/ultralytics."},{"key":"ref_40","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Doll\u00e1r, P., and Zitnick, C.L. (2014). Microsoft COCO: Common Objects in Context. European Conference on Computer Vision, Springer.","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref_41","doi-asserted-by":"crossref","unstructured":"Selvaraju, R.R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., and Batra, D. (2017). Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization. Proceedings of the IEEE ICCV, IEEE.","DOI":"10.1109\/ICCV.2017.74"},{"key":"ref_42","doi-asserted-by":"crossref","unstructured":"Chattopadhay, A., Sarkar, A., Howlader, P., and Balasubramanian, V.N. (2018). Grad-CAM++: Generalized Gradient-based Visual Explanations for Deep Convolutional Networks. Proceedings of the IEEE WACV, IEEE.","DOI":"10.1109\/WACV.2018.00097"},{"key":"ref_43","doi-asserted-by":"crossref","unstructured":"Muhammad, M.B., and Yeasin, M. (2020). Eigen-CAM: Class Activation Map using Principal Components. Proceedings of the International Joint Conference on Neural Networks (IJCNN), IEEE.","DOI":"10.1109\/IJCNN48605.2020.9206626"},{"key":"ref_44","unstructured":"Sapkota, R., Bhattarai, B., Davison, A.J., and Kim, D. (2026). YOLO26: Key Architectural Enhancements and Performance Benchmarking for Real-Time Object Detection. arXiv."},{"key":"ref_45","doi-asserted-by":"crossref","unstructured":"Urbina-Dominguez, E.J., Lizarbe-Alarcon, H., Galvez-Gastelu, Y., Porras-Flores, E.E., Moncada-Sosa, W., Estrada-Cardenas, J.E., Leon-Palacios, E., and Tenorio-Huarancca, D.O. (2026). ADAS-TSR: A Deep Learning-Based Traffic Sign Recognition System with Voice Alerts for Andean Historic City Centers. Appl. Sci., 16.","DOI":"10.3390\/app16062664"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/8\/2569\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,28]],"date-time":"2026-04-28T08:17:06Z","timestamp":1777364226000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/8\/2569"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,21]]},"references-count":45,"journal-issue":{"issue":"8","published-online":{"date-parts":[[2026,4]]}},"alternative-id":["s26082569"],"URL":"https:\/\/doi.org\/10.3390\/s26082569","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4,21]]}}}