Traffic sign detection (TSD) using convolutional neural networks (CNN) is promising and intriguing for autonomous driving. Especially, with sophisticated large-scale CNN models, TSD can be performed with high accuracy. However, the conventional CNN models suffer the drawbacks of being time-consuming and resource-hungry, which limit their application and deployments in various platforms of limited resources. In this paper, we propose a novel real-time traffic sign detection system with a lightweight backbone network named Depth Separable DetNet (DS-DetNet) and a lite fusion feature pyramid network (LFFPN) for efficient feature fusion. The new model can achieve a performance trade-off between speed and accuracy using a depthwise separable bottleneck block, a lite fusion module, and an improved SSD detection front-end. The testing results on the MS COCO and the GTSDB datasets reveal that 23.1% mAP with 6.39 M parameters and only 1.08B FLOPs on MSCOCO, 81.35% mAP with 5.78 M parameters on GTSDB. With our model, the run speed is 61 frames per second (fps) on GTX 1080ti, 12 fps on Nvidia Jetson Nano and 16 fps on Nvidia Jetson Xavier NX.

使用卷积神经网络（CNN）的交通标志检测（TSD）对于自动驾驶很有前途，并且很有趣。特别是，使用复杂的大型CNN模型，可以高精度执行TSD。但是，常规的CNN模型具有耗时且资源匮乏的缺点，这限制了它们在有限资源的各种平台中的应用和部署。在本文中，我们提出了一种新颖的实时交通标志检测系统，该系统具有名为“深度可分离DetNet（DS-DetNet）”的轻量级骨干网络和用于有效特征融合的精巧融合特征金字塔网络（LFFPN）。使用深度可分离瓶颈模块，轻型融合模块和改进的SSD检测前端，新模型可以在速度和精度之间实现性能折衷。在MS COCO和GTSDB数据集上的测试结果表明，mAP的参数为6.39 M，mCO仅为1.08B FLOPs； GTSDB的参数为5.78 M，mAP为81.35％，mAP为81.35％。使用我们的模型，运行速度在GTX 1080ti上为61帧/秒（fps），在Nvidia Jetson Nano上为12 fps，在Nvidia Jetson Xavier NX上为16 fps。