Autonomous vehicle refers to a vehicle capable of perceiving its surrounding environment and driving with little or no human driver input. The perception system is a fundamental component which enables the autonomous vehicle to collect data and extract relevant information from the environment to drive safely. Benefit from the recent advances in computer vision, the perception task can be achieved by using sensors, such as camera, LiDAR, radar, and ultrasonic sensor. This paper reviews publications on computer vision and autonomous driving that are published during the last ten years. In particular, we first investigate the development of autonomous driving systems and summarize these systems that are developed by the major automotive manufacturers from different countries. Second, we investigate the sensors and benchmark data sets that are commonly utilized for autonomous driving. Then, a comprehensive overview of computer vision applications for autonomous driving such as depth estimation, object detection, lane detection, and traffic sign recognition are discussed. Additionally, we review public opinions and concerns on autonomous vehicles. Based on the discussion, we analyze the current technological challenges that autonomous vehicles meet with. Finally, we present our insights and point out some promising directions for future research. This paper will help the reader to understand autonomous vehicles from the perspectives of academia and industry.

翻译：自动驾驶车辆是指能够在极少或无需人类驾驶员干预的情况下感知周围环境并行驶的车辆。感知系统是实现自动驾驶车辆安全行驶的基础组件，它能从环境中收集数据并提取相关信息。得益于计算机视觉领域的最新进展，感知任务可以通过使用摄像头、激光雷达（LiDAR）、雷达和超声波传感器等传感器来完成。本文综述了过去十年间发表的关于计算机视觉和自动驾驶的文献。具体而言，我们首先调查了自动驾驶系统的发展历程，并总结了不同国家主要汽车制造商开发的此类系统。其次，研究了自动驾驶中常用的传感器和基准数据集。随后，全面讨论了计算机视觉在自动驾驶中的应用，例如深度估计、目标检测、车道检测和交通标志识别。此外，我们还回顾了公众对自动驾驶车辆的观点和关切。基于上述讨论，分析了当前自动驾驶车辆面临的技术挑战。最后，提出了我们的见解，并指出了未来研究的若干有前景的方向。本文将从学术界和工业界的视角帮助读者理解自动驾驶车辆。