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

Visual Odometry and 3D Point Clouds under Low-light Conditions

Zhang, Hongmou and Ernst, Ines and Zuev, Sergey and Börner, Anko and Knoche, Martin and Klette, Reinhard (2018) Visual Odometry and 3D Point Clouds under Low-light Conditions. Image and Vision Computing New Zealand 2018, 19-21 November, 2018, Auckland, New Zealand.

[img] PDF - Registered users only
5MB

Official URL: http://ivcnz2018.massey.ac.nz/

Abstract

The paper discusses an evaluation of visual odometry accuracy with respect to available lighting. Very extensive test data (along one country-side road in New Zealand) have been recorded at day and at night. Used sensors are stereo cameras and an inertial measurement unit (IMU). The paper discusses odometry results for the cases when using visual odometry only (i.e. based on the stereo camera data), or additionally also using the IMU. The paper also presents 3D point cloud reconstruction under low-light conditions by using visual odometry and IMU combined.

Item URL in elib:https://elib.dlr.de/125394/
Document Type:Conference or Workshop Item (Speech)
Title:Visual Odometry and 3D Point Clouds under Low-light Conditions
Authors:
AuthorsInstitution or Email of AuthorsAuthors ORCID iD
Zhang, HongmouHongmou.Zhang (at) dlr.deUNSPECIFIED
Ernst, InesUNSPECIFIEDUNSPECIFIED
Zuev, SergeyUNSPECIFIEDUNSPECIFIED
Börner, AnkoAnko.Boerner (at) dlr.deUNSPECIFIED
Knoche, MartinUNSPECIFIEDUNSPECIFIED
Klette, ReinhardUNSPECIFIEDUNSPECIFIED
Date:19 November 2018
Refereed publication:Yes
Open Access:No
Gold Open Access:No
In SCOPUS:No
In ISI Web of Science:No
Status:Published
Keywords:IMU, visual odometry, Low-light Conditions, integrated positioning system
Event Title:Image and Vision Computing New Zealand 2018
Event Location:Auckland, New Zealand
Event Type:international Conference
Event Dates:19-21 November, 2018
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: Berlin-Adlershof
Institutes and Institutions:Institute of Optical Sensor Systems > Real-Time Data Processing
Deposited By: Zhang, Hongmou
Deposited On:08 Jan 2019 09:30
Last Modified:08 Jan 2019 09:30

Repository Staff Only: item control page

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