A Coarse-to-Fine Deep Learning Based Framework for Traffic Light Recognition
Authors:
- 29 April 2024
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Transportation Systems
- Vol. 25 (10) , 13887-13899
Abstract
Accurate recognition of traffic light plays a crucial role in ensuring road traffic safety. Due to the wide variety of traffic light classes and the inherent conflict between location determination and intra-class classification of traffic lights, existing deep learning-based methods cannot obtain satisfactory results, making them still unreliable as traffic light recognizers. To address this issue, we propose an effective Coarse-to-fine framework for traffic light recognition, which is consisted of an enhanced super class detector and a fine-grained classifier. The main contributions lie in three aspects. Firstly, we determine the optimal number of super class by adopting a clustering algorithm. It can alleviate the effect caused by similar classes of traffic light. Secondly, we enhance the super class detector by introducing an additional prediction layer, which enable utilizing the shadow features and improving the detection performance of traffic light super class. Lastly, we propose a fine-grained classifier based on depth-wise separable convolution and expansion layer for super class candidate classification. It can achieve superior recognition performance of different traffic lights especially for similar classes. To evaluate the effectiveness of our method, we conduct experiments on WPI (Worcester Polytechnic Institute) traffic light dataset. With an input size of 416 ${\times}$ 416 pixels, the proposed method can achieve a precision of 99.04% and a recall of 97.40% with a speed of 9.9ms. Compared with other state-of-the-art methods, the results demonstrate the significant competitiveness of our method and its high effectiveness for traffic light recognition.Keywords
Funding Information
- Science and Technology Innovation Key Research and Development Program of Chongqing (CSTB2023TIAD-STX0030)
- Guangdong Province key Field Research and Development Plan Project (2022B0701180001)
- Guangdong Basic and Applied Basic Research Foundation (2022A1515010692)
- International Program Fund for Young Talent Scientific Research People, Sun Yat-Sen University
- Fourth Xijiang Innovation and Entrepreneurship Team and Leader Project of Zhaoqing, China
This publication has 42 references indexed in Scilit:
- Map aided visual-inertial fusion localization method for autonomous driving vehiclesMeasurement, 2023
- Collision-avoidance lane change control method for enhancing safety for connected vehicle platoon in mixed traffic environmentAccident Analysis & Prevention, 2023
- SPaT/MAP V2X communication between traffic light and vehicles and a realization with digital twinComputers and Electrical Engineering, 2022
- Lane change strategy analysis and recognition for intelligent driving systems based on random forestExpert Systems with Applications, 2021
- Self-driving cars: A surveyExpert Systems with Applications, 2021
- Traffic-light sign recognition using capsule networkMultimedia Tools and Applications, 2021
- MBBNet: An edge IoT computing-based traffic light detection solution for autonomous busJournal of Systems Architecture, 2020
- Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based LocalizationInternational Journal of Computer Vision, 2019
- Accurate traffic light detection using deep neural network with focal regression lossImage and Vision Computing, 2019
- Feature representation for statistical-learning-based object detection: A reviewPattern Recognition, 2015