Due to the unavailability of Vehicle-to-Infrastructure (V2I) communication in current transportation systems, Traffic Light Detection (TLD) is still considered an important module in autonomous vehicles and Driver Assistance Systems (DAS). To overcome low flexibility and accuracy of vision-based heuristic algorithms and high power consumption of deep learning-based methods, we propose a lightweight and real-time traffic light detector for the autonomous vehicle platform. Our model consists of a heuristic candidate region selection module to identify all possible traffic lights, and a lightweight Convolution Neural Network (CNN) classifier to classify the results obtained. Offline simulations on the GPU server with the collected dataset and several public datasets show that our model achieves higher average accuracy and less time consumption. By integrating our detector module on NVidia Jetson TX1/TX2, we conduct on-road tests on two full-scale self-driving vehicle platforms (a car and a bus) in normal traffic conditions. Our model can achieve an average detection accuracy of 99.3 percent (mRttld) and 99.7 percent (Rttld) at 10Hz on TX1 and TX2, respectively. The on-road tests also show that our traffic light detection module can achieve $<\pm\; 1.5m$<±1.5m errors at stop lines when working with other self-driving modules.

中文翻译：

---

用于自动驾驶车辆的基于深度 CNN 的实时交通灯检测器

由于当前交通系统中车辆对基础设施 (V2I) 通信不可用，交通灯检测 (TLD) 仍被认为是自动驾驶汽车和驾驶员辅助系统 (DAS) 中的重要模块。为了克服基于视觉的启发式算法的低灵活性和准确性以及基于深度学习的方法的高功耗，我们提出了一种用于自动驾驶汽车平台的轻量级实时交通灯检测器。我们的模型由一个启发式候选区域选择模块组成，用于识别所有可能的交通灯，以及一个轻量级卷积神经网络 (CNN) 分类器，用于对获得的结果进行分类。使用收集的数据集和几个公共数据集在 GPU 服务器上进行离线模拟表明，我们的模型实现了更高的平均精度和更少的时间消耗。通过在 NVidia Jetson TX1/TX2 上集成我们的检测器模块，我们在正常交通条件下对两个全尺寸自动驾驶车辆平台（汽车和公共汽车）进行了道路测试。我们的模型可以在 TX1 和 TX2 上分别在 10Hz 下实现 99.3% (mRttld) 和 99.7% (Rttld) 的平均检测精度。道路测试也表明我们的交通灯检测模块可以实现$<\下午\; 150 万美元<±1.5米 与其他自动驾驶模块一起工作时停止线处的错误。