Deep learning-based perception systems for autonomous driving: A comprehensive survey

Abstract

With the rapid development of society and the economy, autonomous driving techniques are widely applied in many areas, such as autonomous vehicles, autonomous drones, and robotics. As a dominating technique, deep learning has become more and more popular for 2-D and 3-D object detection. Numerous deep learning-based methods have been proposed to solve various vision issues. To further help with the development of unmanned systems, this paper presents a comprehensive survey of the recent processes from the past five years for 3-D object detection, road detection, traffic sign detection, and traffic light detection and classification. To summarize and analyze previous works in detail, this paper only focuses on deep learning-based object detection tasks in autonomous driving that take place when the input is a point cloud or image(s). It also presents comparative results for insight comparison and inspiring future researches.