Real-time and fast recognition of all kinds of traffic participants in intelligent driving has always been a major difficulty in the research of internet of vehicles. With the advent of edge computing, we try to deploy an image recognition algorithm directly to the intelligent vehicles. However, the original image recognition algorithm is difficult to be directly deployed on the vehicles due to limited edge device resources. Based on this, a fast recognition model of vulnerable traffic participants based on depthwise separable convolutional neural network (DSCYOLO) is proposed in this paper. The algorithm can significantly reduce the convolutional parameter quantity and computing load, making it suitable for deployment on the vehicle-mounted edge embedded devices. In order to validate the effectiveness of the proposed method, its simulation results are compared with the main target detection models Faster R-CNN, SSD and YOLOv3. The results show that the recognition time of the proposed model is reduced by 80.28%, 66.80% and 86.74%, respectively, on the basis of a relatively high recognition precision. The model can realize real-time detection and fast recognition of vulnerable traffic participants, so as to avoid a large number of traffic accidents. It has significant social and economic benefits.

智能驾驶中对各类交通参与者的实时快速识别一直是车联网研究的一大难点。随着边缘计算的出现，我们尝试将图像识别算法直接部署到智能车辆上。然而，由于边缘设备资源有限，原始图像识别算法很难直接部署在车辆上。基于此，本文提出了一种基于深度可分离卷积神经网络（DSCYOLO）的弱势交通参与者快速识别模型。该算法可以显着降低卷积参数量和计算量，适合部署在车载边缘嵌入式设备上。为了验证所提出方法的有效性，其仿真结果与主要目标检测模型Faster R-CNN、SSD和YOLOv3进行了对比。结果表明，该模型在较高识别精度的基础上，识别时间分别降低了80.28%、66.80%和86.74%。该模型可以实现对弱势交通参与者的实时检测和快速识别，从而避免大量交通事故的发生。具有显着的社会效益和经济效益。从而避免了大量的交通事故。具有显着的社会效益和经济效益。从而避免了大量的交通事故。具有显着的社会效益和经济效益。