Project AutoVision: Localization and 3D Scene Perception for an Autonomous Vehicle with a Multi-Camera System
Paper in proceeding, 2019
Project AutoVision aims to develop localization and 3D scene perception capabilities for a self-driving vehicle. Such capabilities will enable autonomous navigation in urban and rural environments, in day and night, and with cameras as the only exteroceptive sensors. The sensor suite employs many cameras for both 360-degree coverage and accurate multi-view stereo; the use of low-cost cameras keeps the cost of this sensor suite to a minimum. In addition, the project seeks to extend the operating envelope to include GNSS-less conditions which are typical for environments with tall buildings, foliage, and tunnels. Emphasis is placed on leveraging multi-view geometry and deep learning to enable the vehicle to localize and perceive in 3D space. This paper presents an overview of the project, and describes the sensor suite and current progress in the areas of calibration, localization, and perception.
Author
Lionel Heng
DSO National Laboratories
Benjamin Choi
DSO National Laboratories
Zhaopeng Cui
Swiss Federal Institute of Technology in Zürich (ETH)
Marcel Geppert
Swiss Federal Institute of Technology in Zürich (ETH)
Sixing Hu
National University of Singapore (NUS)
Benson Kuan
DSO National Laboratories
Peidong Liu
Swiss Federal Institute of Technology in Zürich (ETH)
Rang Nguyen
National University of Singapore (NUS)
Ye Chuan Yeo
DSO National Laboratories
Andreas Geiger
Max Planck Society
University of Tübingen
Gim Hee Lee
National University of Singapore (NUS)
Marc Pollefeys
Swiss Federal Institute of Technology in Zürich (ETH)
Microsoft
Torsten Sattler
Chalmers, Electrical Engineering, Signal Processing and Biomedical Engineering
Proceedings - IEEE International Conference on Robotics and Automation
10504729 (ISSN)
Vol. 2019-May 4695-4702978-1-5386-6026-3 (ISBN)
Subject Categories
Embedded Systems
Robotics
Computer Vision and Robotics (Autonomous Systems)
DOI
10.1109/ICRA.2019.8793949
ISBN
9781538660263