Traffic Light Recognition using Convolutional Neural Networks: A Survey
This work provides a structured review for researchers and practitioners in autonomous driving, but it is incremental as it synthesizes existing methods without introducing new techniques.
The paper tackles the lack of a cohesive overview of traffic light recognition methods for autonomous driving by conducting a comprehensive survey and analysis of convolutional neural network (CNN) approaches, clustering them into three groups based on architecture and discussing datasets and research gaps.
Real-time traffic light recognition is essential for autonomous driving. Yet, a cohesive overview of the underlying model architectures for this task is currently missing. In this work, we conduct a comprehensive survey and analysis of traffic light recognition methods that use convolutional neural networks (CNNs). We focus on two essential aspects: datasets and CNN architectures. Based on an underlying architecture, we cluster methods into three major groups: (1) modifications of generic object detectors which compensate for specific task characteristics, (2) multi-stage approaches involving both rule-based and CNN components, and (3) task-specific single-stage methods. We describe the most important works in each cluster, discuss the usage of the datasets, and identify research gaps.