Low-Speed Collision Prevention Warning for Intelligent Vehicles based on Digital Twin and Deep Learning

The low-speed collision prevention warning system for intelligent vehicles is a critical safety technology aimed at reducing low-speed road collision accidents. This study introduces an intelligent vehicle low-speed collision prevention warning method based on digital twin technology and deep learning algorithms. Firstly, a digital twin model was constructed to simulate the vehicle and its surrounding environment, providing a better understanding of the road situation. Subsequently, convolutional neural networks (CNNs) were employed for object detection, identifying other vehicles and obstacles from video frames captured by the vehicle’s front camera. On this basis, a spatial attention mechanism was introduced to reduce the impact of irrelevant targets on collision prediction, thereby improving the system’s accuracy. Through motion tracking, collision prediction, and warning decision-making, the system can detect potential collision hazards and provide timely warnings to the driver, helping to reduce the occurrence of low-speed collision accidents. The experimental results indicate that the method has achieved good performance in various road scenarios, showing potential for playing a crucial role in the safety of intelligent vehicles and road safety. This study provides new insights and approaches for low-speed collision prevention technology in the field of intelligent vehicles.