arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2107.08862cs.CV
收藏

解缠与矢量化:一种基于全景鱼眼相机的自动驾驶三维视觉感知方法

Disentangling and Vectorization: A 3D Visual Perception Approach for Autonomous Driving Based on Surround-View Fisheye Cameras

Zongmu Technology(纵目科技);Karlsruhe Institute of Technology(卡尔斯鲁厄理工学院)

Zizhang Wu, Wenkai Zhang, Jizheng Wang, Man Wang, Yuanzhu Gan, Xinchao Gou, Muqing Fang, Jing Song

摘要:

对于低成本的城市自动驾驶来说,具有环绕视角鱼眼相机系统的车辆的3D视觉感知是一项关键且具有挑战性的任务。虽然现有的单目3D目标检测方法在用于大规模生产的鱼眼图像上表现得不够好,部分原因是缺乏这种图像的3D数据集。本文通过将三维目标检测任务分解为车辆接触点检测、类型分类、再识别和单元组装等子任务,克服和避免了获取大规模精确三维标注真值数据的困难。我们提出了多维向量的概念,以包含不同维度和阶段产生的可利用信息,而不是鸟瞰图(BEV)或八点立方体的描述性方法。真实鱼眼图像的实验表明,我们的解决方案达到了最先进的精度,同时在实践中是实时的。

英文摘要:

The 3D visual perception for vehicles with the surround-view fisheye camera system is a critical and challenging task for low-cost urban autonomous driving. While existing monocular 3D object detection methods perform not well enough on the fisheye images for mass production, partly due to the lack of 3D datasets of such images. In this paper, we manage to overcome and avoid the difficulty of acquiring the large scale of accurate 3D labeled truth data, by breaking down the 3D object detection task into some sub-tasks, such as vehicle's contact point detection, type classification, re-identification and unit assembling, etc. Particularly, we propose the concept of Multidimensional Vector to include the utilizable information generated in different dimensions and stages, instead of the descriptive approach for the bird's eye view (BEV) or a cube of eight points. The experiments of real fisheye images demonstrate that our solution achieves state-of-the-art accuracy while being real-time in practice.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑