Embedded System Vehicle Based on Multi-Sensor Fusion

As intelligent driving vehicles came out of concept into people’s life, the combination safe and artificial intelligence becomes new direction future transportation development. Autonomous technology is developing based on control algorithms model recognitions. In this paper, a cloud-based interconnected multi-sensor fusion autonomous vehicle system proposed that uses deep learning (YOLOv4) improved ORB to identify pedestrians, vehicles, various traffic signs. A interactive built enable owners master situation their at any time. order meet multiple application automatic environment perception processing has broadened by being equipped with speech recognition (ASR), following mode road patrol mode. These functions be used in applications such as agricultural irrigation, firefighting contactless delivery under coronavirus outbreaks. Finally, using embedded equipment, an car was for experimental verification, overall accuracy over 96%.