Smart City Gnosys
Smart city article details
| Title | Towards Efficient Traffic Light Detection And Attribute Recognition System In Open-World Complex Environments |
|---|---|
| ID_Doc | 58121 |
| Authors | Chen Y.; Zhou J.; Duan X.; Lin C.; Zhu X.; Tian D. |
| Year | 2024 |
| Published | Proceedings of 2024 IEEE International Conference on Unmanned Systems, ICUS 2024 |
| DOI | http://dx.doi.org/10.1109/ICUS61736.2024.10839884 |
| Abstract | Traffic lights are one of the most crucial elements of autonomous driving and smart cities to guarantee seamless and unobstructed road operation. With the motivation of designing redundancy mechanisms of cooperative vehicle infrastructure (CVI) system, this work aims to explore an effective and efficient traffic-light perception system based on vehicle-mounted cameras. Considering the scarcity of large-scale datasets for real-world scenarios in China, a traffic light detection and attribute (TL-DR) dataset is constructed. Additionally, a two-stage intelligent perception system, primarily consisting of lightweight detection and a multi-task network for color, arrow, and temporal attributes, is developed to guarantee stability and scalability. Considering the impact alterations in illumination and distance on detections, we optimized the generic detector YOLOv5-s to accommodate objects with small sizes at long distances. Furthermore, this work integrates the digital recognition of countdowns with the classification of color and orientation attributes into a multi-task framework to reduce the inference time. Extensive experiments conducted on the TL-DR database have demonstrated that the proposed system satisfies the real-time and high-precision requirements of vehicle safety while exhibiting good adaptability under challenging driving scenarios. The details will be available on https://github.com/pupu-chenyanyan/YOLO-TLR. © 2024 IEEE. |
| Author Keywords | autonomous driving; object detection; perception system; traffic lights |
Similar Articles
| Id | Similarity | Authors | Title | Published |
|---|---|---|---|---|
35413  | 0.876 | Munir S.; Lin H.-Y. | Lnt-Yolo: A Lightweight Nighttime Traffic Light Detection Model | Smart Cities, 8, 3 (2025) |
| 27022 | 0.873 | Darwish F.; Ayman M.; Mohammed A. | Framework For Adaptive Traffic Light System | 2nd International Conference of Intelligent Methods, Systems and Applications, IMSA 2024 (2024) |
| 21798 | 0.867 | Hazarika A.; Choudhury N.; Nasralla M.M.; Khattak S.B.A.; Rehman I.U. | Edge Ml Technique For Smart Traffic Management In Intelligent Transportation Systems | IEEE Access, 12 (2024) |
| 58671 | 0.864 | Bahadure N.B.; Patil P.D.; Birewar R.; Nayyar P.; Shrivastav A.; Oberoi M. | Traffic Signal Detection And Recognition From Real-Scenes Using Yolo | 2023 IEEE Engineering Informatics, EI 2023 (2023) |
| 40922 | 0.86 | Duc Q.-A.N.; Kim T.D.; Nguyen Q.-C.; Thi T.H.N.; Vu Q.; Xuan M.-D.D.; Nguyen V.-N. | Optimizing Traffic Light Control Using Yolov8 For Real-Time Vehicle Detection And Traffic Density | Proceedings of the 2024 9th International Conference on Integrated Circuits, Design, and Verification, ICDV 2024 (2024) |
| 62130 | 0.852 | Vijay Ganesh P.; Sam Joshua V.; Saro Murugan L.; Mahalakshmi S. | Yolov9 Driven Internet Of Things Enabled Sustainable Solution For Intelligent Traffic Light Management System For Emergency Vehicles In Large Scale Urban Traffic | 2nd International Conference on Machine Learning and Autonomous Systems, ICMLAS 2025 - Proceedings (2025) |
| 17852 | 0.851 | Rangari A.P.; Chouthmol A.R.; Kadadas C.; Pal P.; Kumar Singh S. | Deep Learning Based Smart Traffic Light System Using Image Processing With Yolo V7 | 4th International Conference on Circuits, Control, Communication and Computing, I4C 2022 (2022) |