Topometric Maps of Indoor Environments
Extraction, matching and fusion
M.F. van Schendel (TU Delft - Architecture and the Built Environment)
E. Verbree – Mentor (TU Delft - GIS Technologie)
P. Nourian – Graduation committee member (TU Delft - Design Informatics)
R.L. Voûte – Coach (TU Delft - GIS Technologie)
More Info
expand_more
Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.
Abstract
The merging of multiple partial maps of indoor environments created
by teams of human or robot agents into a single global map is a key problem
that, when solved, can improve mapping speed and quality. Existing map
merging approaches generally depend on external signals which are not available indoors or only use the geometric properties of an environment. Inspired by the human understanding of environments in relationship to their context we propose a map merging system that extracts and uses topometric maps, a map representation containing both the geometric and topological characteristics of an environments, to solve the map merging problem in indoor spaces. In this research we demonstrate an intuitive approach to extracting topometric maps of 3D, multi-floor, indoor environments and use both the topological and geometric characteristics contained in the topometric maps to perform context-aware map matching and fusion.