Project AutoVision: Localization and 3D Scene Perception for an Autonomous Vehicle with a Multi-Camera System
Paper i 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.
Författare
Lionel Heng
DSO National Laboratories
Benjamin Choi
DSO National Laboratories
Zhaopeng Cui
Eidgenössische Technische Hochschule Zürich (ETH)
Marcel Geppert
Eidgenössische Technische Hochschule Zürich (ETH)
Sixing Hu
Universiti Kebangsaan Singapura (NUS)
Benson Kuan
DSO National Laboratories
Peidong Liu
Eidgenössische Technische Hochschule Zürich (ETH)
Rang Nguyen
Universiti Kebangsaan Singapura (NUS)
Ye Chuan Yeo
DSO National Laboratories
Andreas Geiger
Max-Planck-Gesellschaft
Universität Tübingen
Gim Hee Lee
Universiti Kebangsaan Singapura (NUS)
Marc Pollefeys
Eidgenössische Technische Hochschule Zürich (ETH)
Microsoft
Torsten Sattler
Chalmers, Elektroteknik, Signalbehandling och medicinsk teknik
Proceedings - IEEE International Conference on Robotics and Automation
10504729 (ISSN)
4695-4702978-1-5386-6026-3 (ISBN)
Ämneskategorier
Inbäddad systemteknik
Robotteknik och automation
Datorseende och robotik (autonoma system)
DOI
10.1109/ICRA.2019.8793949
ISBN
9781538660263