With the rapid development of unmanned driving technology of intelligent networked vehicles,obstacle detection,as one of its core technologies,is very important to ensure driving safety.In this study,we propose a deep learning-based obstacle detection method for unmanned driving of intelligent networked vehicles,which achieves efficient and accurate obstacle detection in complex and changeable road scenarios by constructing an optimized Convolutional Neural Network(CNN)model and combining multi-sensor fusion technology.Experimental results show that the proposed method is significantly better than the traditional method in terms of detection accuracy,real-time performance and robustness,which provides strong support for the development of unmanned driving technology.
关键词
深度学习/智能网联汽车无人驾驶/障碍物检测/卷积神经网络/多传感器融合
Key words
Deep Learning/Autonomous Driving of Intelligent Networked Vehicles/Obstacle Detection/Convolutional Neural Network/Multi-sensor Fusion
维普
万方数据