ADAS-TSR: A Deep Learning-Based Traffic Sign Recognition System with Voice Alerts for Andean Historic City Centers
Authors:
- Eduardo J. Urbina-DominguezEUEduardo J. Urbina-Dominguez
- Hemerson Lizarbe-AlarconHLHemerson Lizarbe-Alarcon
- Yuri Galvez-GasteluYGYuri Galvez-Gastelu
- Efrain E. Porras-FloresEPEfrain E. Porras-Flores
- Wilmer E. Moncada-SosaWMWilmer E. Moncada-Sosa
- Jose E. Estrada-CardenasJEJose E. Estrada-Cardenas
- Edward Leon-PalaciosELEdward Leon-Palacios
- Diego O. Tenorio-HuaranccaDTDiego O. Tenorio-Huarancca
Open Access
- 11 March 2026
- journal article
- research article
- Published by MDPI AG in Applied Sciences
- Vol. 16 (6) , 2664
Abstract
Colonial historic city centers represent a paradigmatic challenge for modern road safety, as they are characterized by narrow streets originally designed for carriage and pedestrian traffic. This research presents ADAS-TSR, a deep learning-based advanced driver assistance system for vertical traffic sign detection with voice alerts, specifically designed for the Historic Center of Ayacucho, Peru, which is located at 2761 m a.s.l. An original dataset comprising 2250 images with 2450 instances corresponding to 14 sign classes according to Peruvian regulations was constructed. The dataset was captured under real operational conditions, including deteriorated, partially occluded, and vehicle impact-deformed signage. A comprehensive multi-model benchmark experiment was conducted, comparing four CNN-based detectors (YOLOv8m, YOLO11n, YOLO26n, YOLO26s) and one transformer-based detector (RT-DETR-l) spanning both classical and state-of-the-art architectures released through January 2026. YOLO26s achieved the best overall performance, with an mAP@0.5 of 0.994 and mAP@0.5:0.95 of 0.989 while using only 9.5 M parameters. YOLO11n matched the performance of YOLOv8m with 10× fewer parameters (2.6 M vs. 25.9 M). Uncertainty analysis revealed that modern architectures exhibit significantly higher prediction confidence (mean > 0.90) compared to YOLOv8m (0.82), and fairness analysis confirmed equitable detection across all 14 classes (Gini < 0.002). A voice alert system with five priority levels and rule-based temporal filtering for detection stabilization was implemented. Validation across five urban circuits spanning 14.11 km demonstrated a detection rate of 94.7% with a 73% reduction in redundant alerts.Keywords
This publication has 34 references indexed in Scilit:
- Traffic sign dataset for connected and automated vehicle operations in rural areasData in Brief, 2025
- FAIERDet: Fuzzy-based adaptive image enhancement for real-time traffic sign detection and recognition under varying light conditionsExpert Systems with Applications, 2025
- DP-YOLO: A lightweight traffic sign detection model for small object detectionDigital Signal Processing, 2025
- SAAM-ReflectNet: Sign-aware attention-based multitasking framework for integrated traffic sign detection and retroreflectivity estimationExpert Systems with Applications, 2025
- Assessing YOLO models for real-time object detection in urban environments for advanced driver-assistance systems (ADAS)Alexandria Engineering Journal, 2025
- TSD-DETR: A lightweight real-time detection transformer of traffic sign detection for long-range perception of autonomous drivingEngineering Applications of Artificial Intelligence, 2024
- A universal traffic sign detection system using a novel self-training neural network modeling approachAdvanced Engineering Informatics, 2024
- EDN-YOLO: Multi-scale traffic sign detection method in complex scenesDigital Signal Processing, 2024
- Mexican traffic sign detection and classification using deep learningExpert Systems with Applications, 2022
- LabelMe: A Database and Web-Based Tool for Image AnnotationInternational Journal of Computer Vision, 2007