Benchmarking Recent YOLO Architectures for Detecting Vehicles, Pedestrians, and Motorcycles at Complex Urban Intersections: Evidence from a Hybrid Mexico City–LISA Dataset
Open Access
- 22 September 2026
- journal article
- research article
- Published by MDPI AG in Smart Cities
- Vol. 9 (10) , 160
Abstract
Urban road user detection supports safety-critical applications in Intelligent Transportation Systems, but architecture assessment requires balancing predictive performance with computational efficiency under controlled and leakage-aware evaluation conditions. This study adopts a three-stage benchmarking framework for vehicle, motorcycle, and pedestrian detection using a hybrid dataset of 4983 images derived from LISA and traffic scenes captured at 18 complex intersections in Mexico City. Stage I provides an exploratory comparison of six medium-sized YOLO architectures (YOLOv8m, YOLOv9m, YOLOv10m, YOLOv11m, YOLOv12m, and YOLOv26m), whereas Stage II restricts leakage-controlled confirmatory evaluation to three selected architectures: YOLOv10m, YOLOv11m, and YOLOv26m. Stage III examines the corresponding YOLOv10n and YOLOv26n nano variants. Both sources were manually annotated under a unified three-class protocol, producing 3483 quantitative images with 6624 ground truth instances and 1500 images for qualitative inference. Annotation reproducibility reached a mean pairwise IoU of 0.85 ± 0.11 and Fleiss’ κ of 0.968. A retrospective audit of the original image-level split identified acquisition group overlap and confirmed near duplicates across partitions. A corrected group-disjoint split eliminated shared groups, exact duplicates, and confirmed near duplicates while preserving the aggregate source and class distributions. Under three-seed leakage-controlled confirmatory evaluation, YOLOv26m achieved the highest mAP@0.50:0.95 among the three Stage II confirmatory models (0.5717 ± 0.0013), followed by YOLOv11m (0.5632 ± 0.0012) and YOLOv10m (0.5516 ± 0.0014), with paired bootstrap analysis supporting all three pairwise differences after Holm correction. Source-specific evaluation revealed consistently lower performance on the Mexico City subset than on LISA. YOLOv11m showed the lowest overall calibration error (ECE = 0.052 ± 0.003). At the nano-scale, YOLOv10n provided higher mAP@0.50:0.95, lower latency, and greater throughput than YOLOv26n, whereas YOLOv26n required fewer GFLOPs and less benchmark energy. The Stage II group-disjoint protocol produced more conservative performance estimates than Stage I; however, the observed mAP reduction cannot be quantified as the effect of leakage removal alone because the two stages also differed in optimization configuration and repeated-run design. These findings support multi-objective model selection based on predictive performance, calibration, latency, complexity, memory, energy consumption, and deployment constraints.Keywords
Funding Information
- Instituto Politécnico Nacional
- Centro de Investigación e Innovación Tecnológica
- Centro de Investigación en Ciencia Aplicada y Tecnología Avanzada, Unidad Legaria (20226880)
- Centro de Investigación en Ciencia Aplicada y Tecnología Avanzada, Unidad Legaria (20254479)
- Centro de Investigación en Ciencia Aplicada y Tecnología Avanzada, Unidad Legaria (20254340)
- Centro de Investigación en Ciencia Aplicada y Tecnología Avanzada, Unidad Legaria (IND-2026-0610)
- Centro de Investigación en Ciencia Aplicada y Tecnología Avanzada, Unidad Legaria (ProRed-2026-0060)
- IPN Computing Network, the Red de Expertos e Innovación Automotriz
- CAPROM
This publication has 46 references indexed in Scilit:
- Roadside Sensor Systems for Vulnerable Road User Protection: A Review of Methods and ApplicationsIEEE Access, 2025
- Urban Traffic Control Meets Decision Recommendation System: A Survey and PerspectiveIEEE/CAA Journal of Automatica Sinica, 2024
- Comparative analysis of multiple YOLO-based target detectors and trackers for ADAS in edge devicesRobotics and Autonomous Systems, 2023
- Deep Multi-Modal Object Detection and Semantic Segmentation for Autonomous Driving: Datasets, Methods, and ChallengesIEEE Transactions on Intelligent Transportation Systems, 2020
- A survey of deep learning techniques for autonomous drivingJournal of Field Robotics, 2019
- Object Detection With Deep Learning: A ReviewIEEE Transactions on Neural Networks and Learning Systems, 2019
- Mask R-CNN2017
- The Cityscapes Dataset for Semantic Urban Scene Understanding2016
- Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation2014
- Vision-Based Traffic Sign Detection and Analysis for Intelligent Driver Assistance Systems: Perspectives and SurveyIEEE Transactions on Intelligent Transportation Systems, 2012