With autonomous driving developing in a booming stage, accurate object detection in complex scenarios attract wide attention to ensure the safety of autonomous driving. Millimeter wave (mmWave) radar and vision fusion is a mainstream solution for accurate obstacle detection. This article presents a detailed survey on mmWave radar and vision fusion based obstacle detection methods. Firstly, we introduce the tasks, evaluation criteria and datasets of object detection for autonomous driving. Then, the process of mmWave radar and vision fusion is divided into three parts: sensor deployment, sensor calibration and sensor fusion, which are reviewed comprehensively. Especially, we classify the fusion methods into data level, decision level and feature level fusion methods. Besides, we introduce the fusion of lidar and vision in autonomous driving in the aspects of obstacle detection, object classification and road segmentation, which is promising in the future. Finally, we summarize this article.

翻译：随着自动驾驶在蓬勃的阶段发展,在复杂情况下准确的物体探测会引起广泛的注意,以确保自动驾驶的安全。毫米波(毫米瓦夫)雷达和视觉融合是准确障碍探测的一种主流解决办法。本文章详细调查了以毫米波雷达和视觉融合为基础的障碍探测方法。首先,我们为自动驾驶引入了物体探测的任务、评价标准和数据集。然后,毫米波雷达和视觉融合过程分为三部分:传感器部署、传感器校准和传感器融合,这些过程经过全面审查。特别是,我们将聚变方法分为数据水平、决定水平和特征水平的聚合方法。此外,我们还在自动驾驶过程中引入了激光雷达和视觉融合,这些方面的障碍探测、物体分类和道路分割都是充满希望的。最后,我们总结了这一条。