DLR-Logo -> http://www.dlr.de
DLR Portal Home | Imprint | Privacy Policy | Contact | Deutsch
Fontsize: [-] Text [+]

3d visual perception for self-driving cars using a multi-camera system: Calibration, mapping, localization, and obstacle detection

Häne, Christian and Heng, Lionel and Lee, Gim Hee and Fraundorfer, Friedrich and Furgale, Paul and Sattler, Torsten and Pollefeys, Marc (2018) 3d visual perception for self-driving cars using a multi-camera system: Calibration, mapping, localization, and obstacle detection. Image and Vision Computing, 68, pp. 14-27. Elsevier. doi: 10.1016/j.imavis.2017.07.003. ISSN 0262-8856.

Full text not available from this repository.

Official URL: http://www.sciencedirect.com/science/article/pii/S0262885617301117


Cameras are a crucial exteroceptive sensor for self-driving cars as they are low-cost and small, provide appearance information about the environment, and work in various weather conditions. They can be used for multiple purposes such as visual navigation and obstacle detection. We can use a surround multi-camera system to cover the full 360-degree field-of-view around the car. In this way, we avoid blind spots which can otherwise lead to accidents. To minimize the number of cameras needed for surround perception, we utilize fisheye cameras. Consequently, standard vision pipelines for 3D mapping, visual localization, obstacle detection, etc. need to be adapted to take full advantage of the availability of multiple cameras rather than treat each camera individually. In addition, processing of fisheye images has to be supported. In this paper, we describe the camera calibration and subsequent processing pipeline for multi-fisheye-camera systems developed as part of the V-Charge project. This project seeks to enable automated valet parking for self-driving cars. Our pipeline is able to precisely calibrate multi-camera systems, build sparse 3D maps for visual navigation, visually localize the car with respect to these maps, generate accurate dense maps, as well as detect obstacles based on real-time depth map extraction.

Item URL in elib:https://elib.dlr.de/115869/
Document Type:Article
Title:3d visual perception for self-driving cars using a multi-camera system: Calibration, mapping, localization, and obstacle detection
AuthorsInstitution or Email of AuthorsAuthor's ORCID iD
Häne, ChristianDepartment of Electrical Engineering and Computer Sciences, University of California BerkeleyUNSPECIFIED
Heng, LionelDepartment of Computer Science, ETH ZürichUNSPECIFIED
Lee, Gim Heemitsubishi electric research laboratories, usaUNSPECIFIED
Fraundorfer, Friedrichfriedrich.fraundorfer (at) dlr.deUNSPECIFIED
Furgale, PaulDepartment of Mechanical and Process Engineering, ETH ZürichUNSPECIFIED
Sattler, TorstenDepartment of Computer Science, ETH ZürichUNSPECIFIED
Pollefeys, Marceth zürich, switzerlandUNSPECIFIED
Journal or Publication Title:Image and Vision Computing
Refereed publication:Yes
Open Access:No
Gold Open Access:No
In ISI Web of Science:Yes
DOI :10.1016/j.imavis.2017.07.003
Page Range:pp. 14-27
Keywords:Fisheye camera; Multi-camera system; Calibration; Mapping; Localization; Obstacle detection
HGF - Research field:Aeronautics, Space and Transport
HGF - Program:Transport
HGF - Program Themes:Terrestrial Vehicles (old)
DLR - Research area:Transport
DLR - Program:V BF - Bodengebundene Fahrzeuge
DLR - Research theme (Project):V - Fahrzeugintelligenz (old)
Location: Oberpfaffenhofen
Institutes and Institutions:Remote Sensing Technology Institute > Photogrammetry and Image Analysis
Deposited By: Zielske, Mandy
Deposited On:29 Nov 2017 17:06
Last Modified:09 Jul 2018 15:38

Repository Staff Only: item control page

Help & Contact
electronic library is running on EPrints 3.3.12
Copyright © 2008-2017 German Aerospace Center (DLR). All rights reserved.