Setting of training parameters.

Automobile intelligence is the trend for modern automobiles, of which environment perception is the key technology of intelligent automobile research. For autonomous vehicles, the detection of object information, such as vehicles and pedestrians in traffic scenes is crucial to improving driving safety. However, in the actual traffic scene, there are many special conditions such as object occlusion, small objects, and bad weather, which will affect the accuracy of object detection. In this research, the SwinT-YOLOv4 algorithm is proposed for detecting objects in traffic scenes, which is based on the YOLOv4 algorithm. Compared with a Convolutional neural network (CNN), the vision transformer is more powerful at extracting vision features of objects in the image. The CNN-based backbone in YOLOv4 is replaced by the Swin Transformer in the proposed algorithm. The feature-fusing neck and predicting head of YOLOv4 is remained. The proposed model was trained and evaluated in the COCO dataset. Experiments show that our method can significantly improve the accuracy of object detection under special conditions. Equipped with our method, the object detection precision for cars and person is improved by 1.75%, and the detection precision for car and person reach 89.04% and 94.16%, respectively.汽车智能化是现代汽车的发展趋势，而环境感知则是智能汽车研发的核心技术。对于自动驾驶车辆而言，检测交通场景中的车辆、行人等目标信息，对提升行车安全性至关重要。然而在实际交通场景中，存在目标遮挡、小目标物体、恶劣天气等诸多特殊工况，这些因素均会对目标检测的精度造成负面影响。本研究提出了一种面向交通场景目标检测的SwinT-YOLOv4算法，该算法以YOLOv4为基础架构。相较于卷积神经网络（Convolutional Neural Network, CNN），视觉Transformer（Vision Transformer）在提取图像中目标的视觉特征方面具备更强的能力。所提算法将YOLOv4中基于卷积神经网络的主干网络替换为Swin Transformer，同时保留了YOLOv4的特征融合颈部网络与预测头模块。本研究在COCO数据集上对所提模型进行了训练与性能评估。实验结果表明，所提方法可显著提升特殊工况下的目标检测精度。搭载本方法后，车辆与行人的目标检测精度分别提升了1.75%，车辆与行人的检测精度分别达到89.04%与94.16%。