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.

翻译：实时交通信号灯识别对于自动驾驶至关重要。然而，目前尚缺乏针对该任务的底层模型架构的统一概述。本文对使用卷积神经网络（CNN）的交通信号灯识别方法进行了全面的综述与分析。我们聚焦于两个核心方面：数据集与CNN架构。基于底层架构，我们将方法归纳为三大类：（1）针对特定任务特征进行改进的通用目标检测器变体；（2）融合基于规则组件与CNN组件的多阶段方法；（3）面向特定任务的单阶段方法。我们描述了每类中最重要的研究工作，讨论了数据集的使用情况，并指出了研究空白。