Change search
ReferencesLink to record
Permanent link

Direct link
Designing a Relational Database for Long-Term Visual Mapping
Halmstad University, School of Information Technology, Halmstad Embedded and Intelligent Systems Research (EIS), CAISR - Center for Applied Intelligent Systems Research. Volkswagen AG.
Autonomous Systems Lab, ETH Z¨urich Leonhardstrasse 21, Z¨urich, Switzerland.
Volkswagen AG, Wolfsburg, Germany .
Halmstad University, School of Information Technology, Halmstad Embedded and Intelligent Systems Research (EIS), CAISR - Center for Applied Intelligent Systems Research.ORCID iD: 0000-0003-3513-8854
(English)Manuscript (preprint) (Other academic)
Abstract [en]

We present a map architecture based on a relational database that helps tackle the challenge of lifelong visuallocalization and mapping. The proposed design is rooted in a set of use-cases that describe the processes necessary for creating, using and analyzing visual maps. Our database and software architecture effectively expresses the requiredinteractions between map elements, such as visual frames generated by multi-camera systems. One of the major strengths of the proposed system is the ease of formulating pertinent and novel queries. We show how these queries can help us gaina better intuition about the map contents, taking into account complex data associations, even as session upon session is added to the map. Furthermore, we demonstrate how referential integrity checks, rollbacks and similar features of relational database management systems are beneficial for building long-term maps. Based on our experience with the proposed system during one year of intensive data collection and analysis, we discuss key lessons learned and indicate directions for evolving its design. These lessons show the importance of using higher relational normal forms to make the database schema even more useful for querying, as well as the need for a distributed, versioned system.

Keyword [en]
Relational Databases, Visual Localization, Mapping, Automated Vehicles
National Category
Electrical Engineering, Electronic Engineering, Information Engineering
URN: urn:nbn:se:hh:diva-28240OAI: diva2:811166

Submitted to: Journal of Software Engineering for Robotics, issn: 2035-3928

Available from: 2015-05-11 Created: 2015-05-11 Last updated: 2016-02-23Bibliographically approved
In thesis
1. Lifelong Visual Localization for Automated Vehicles
Open this publication in new window or tab >>Lifelong Visual Localization for Automated Vehicles
2015 (English)Doctoral thesis, comprehensive summary (Other academic)
Abstract [en]

Automated driving can help solve the current and future problems of individualtransportation. Automated valet parking is a possible approach to help with overcrowded parking areas in cities and make electric vehicles more appealing. In an automated valet system, drivers are able to drop off their vehicle close to a parking area. The vehicle drives to a free parking spot on its own, while the driver is free to perform other tasks — such as switching the mode of transportation. Such a system requires the automated car to navigate unstructured, possibly three dimensional areas. This goes beyond the scope ofthe tasks performed in the state of the art for automated driving.

This thesis describes a visual localization system that provides accuratemetric pose estimates. As sensors, the described system uses multiple monocular cameras and wheel-tick odometry. This is a sensor set-up that is close to what can be found in current production cars. Metric pose estimates with errors in the order of tens of centimeters enable maneuvers such as parking into tight parking spots. This system forms the basis for automated navigationin the EU-funded V-Charge project.

Furthermore, we present an approach to the challenging problem of life-long mapping and localization. Over long time spans, the visual appearance ofthe world is subject to change due to natural and man-made phenomena. The effective long-term usage of visual maps requires the ability to adapt to these changes. We describe a multi-session mapping system, that fuses datasets intoiiia single, unambiguous, metric representation. This enables automated navigation in the presence of environmental change. To handle the growing complexityof such a system we propose the concept of Summary Maps, which contain a reduced set of landmarks that has been selected through a combination of scoring and sampling criteria. We show that a Summary Map with bounded complexity can achieve accurate localization under a wide variety of conditions.

Finally, as a foundation for lifelong mapping, we propose a relational database system. This system is based on use-cases that are not only concerned with solving the basic mapping problem, but also with providing users with a better understanding of the long-term processes that comprise a map. We demonstrate that we can pose interesting queries to the database, that help us gain a better intuition about the correctness and robustness of the created maps. This is accomplished by answering questions about the appearance and distribution of visual landmarks that were used during mapping. This thesis takes on one of the major unsolved challenges in vision-based localization and mapping: long-term operation in a changing environment. We approach this problem through extensive real world experimentation, as well as in-depth evaluation and analysis of recorded data. We demonstrate that accurate metric localization is feasible both during short term changes, as exemplified by the transition between day and night, as well as longer term changes, such as due to seasonal variation.

Place, publisher, year, edition, pages
Halmstad: Halmstad University Press, 2015. 74 p.
Halmstad University Dissertations, 12
vision-based localization, automated vehicles
National Category
Electrical Engineering, Electronic Engineering, Information Engineering
urn:nbn:se:hh:diva-28239 (URN)978-91-87045-27-1 (ISBN)978-91-87045-26-4 (ISBN)
Public defence
2015-05-13, Wigforssalen, Visionen, Kristian IV:s väg 3, 301 18, Halmstad, 13:15 (English)
Available from: 2015-05-12 Created: 2015-05-11 Last updated: 2016-01-08Bibliographically approved

Open Access in DiVA

fulltext(5810 kB)158 downloads
File information
File name FULLTEXT01.pdfFile size 5810 kBChecksum SHA-512
Type fulltextMimetype application/pdf

Search in DiVA

By author/editor
Philippsen, Roland
By organisation
CAISR - Center for Applied Intelligent Systems Research
Electrical Engineering, Electronic Engineering, Information Engineering

Search outside of DiVA

GoogleGoogle Scholar
Total: 158 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

Total: 517 hits
ReferencesLink to record
Permanent link

Direct link