Survey on deep learning-based 3D object detection in autonomous driving
Zhenming Liang, Yingping Huang
Abstract
Autonomous driving technology has entered into the fast lane of development in recent years. An essential component of autonomous driving technology is scene perception, especially 3D object detection. This work gives a comprehensive survey on the up-to-date deep learning-based approaches for 3D object detection in autonomous driving, and categorizes the existing detection models into three classes in terms of their input data format, including LiDAR point cloud-based, Camera RGB image-based, and LiDAR point cloud-camera image fusion-based 3D object detection methods. This work also discusses and analyzes these models according to their characteristics, basic frameworks, advantages and disadvantages, and exhibits the benchmark datasets which are commonly used in the research community. At last, this work summarizes the review work and provides a discussion on the practical challenges and future trend of the research domain.