Designing a Relational Database for Long-Term Visual Mapping
(English)Manuscript (preprint) (Other academic)
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.
Relational Databases, Visual Localization, Mapping, Automated Vehicles
Electrical Engineering, Electronic Engineering, Information Engineering
IdentifiersURN: urn:nbn:se:hh:diva-28240OAI: oai:DiVA.org:hh-28240DiVA: diva2:811166
Submitted to: Journal of Software Engineering for Robotics, issn: 2035-39282015-05-112015-05-112016-02-23Bibliographically approved