Work

Detection of Traffic Lights and Status (Red, Yellow and Green) in Images with Different Environmental Conditions Using Architectures from Yolov8 to Yolov12

Year: 2026

Type: article

Abstract: Given that approximately 70% of traffic accidents are attributable to driver-related factors, it is necessary for vehicles to incorporate technologies that reduce risk through preventive actions derived from traffic-scene analysis. Interpreting the driving environment is non-trivial and is commonly decomposed into sub-tasks; among them, traffic light perception is critical due to its role in regulating vehicular flow. This paper evaluates five YOLO CNN families (YOLOv8–YOLOv12) on two tasks: (i) traffic light detection and (ii) traffic light state recognition (green, yellow, red). The evaluation uses a hybrid dataset comprising the public LISA traffic light dataset and a custom dataset with images from Mexico City captured under diverse lighting conditions—a relevant setting given the city’s high traffic intensity. The results show [email protected] = 94.4–96.3% for traffic light detection and [email protected] = 99.3–99.4% for traffic light state recognition, indicating that modern YOLO variants provide highly reliable performance for both tasks under natural illumination variability.

Source: Vehicles

DOI: 10.3390/vehicles8040090

Authors: Julio Saucedo-Soto, Viridiana Hernández-Herrera, Moisés Márquez-Olivera, Octavio Sánchez-García, Antonio-Gustavo Juárez-Gracia

Institution: Instituto Politécnico Nacional

Language: English

Topic: Advanced Neural Network Applications

Subfield: Computer Vision and Pattern Recognition

Field: Computer Science

Domain: Physical Sciences

SDGs: Sustainable cities and communities, Industry, innovation and infrastructure

Open Access status: gold

Estimated APC paid: $1,930