Gallagher, Louis and McDonald, John (2017) Towards Dense Collaborative Mapping using RGBD Sensors. In: Irish Machine Vision and Image Processing Conference Proceedings 2017. Irish Pattern Recognition & Classification Society, pp. 225-228. ISBN 978-0-9934207-2-6

Preview

Download (181kB) | Preview

Abstract

Development of collaborative, perception driven autonomous systems requires the ability for collaborators to compute a rich, shared representation of the environment, and their place in it, in real-time. Using this shared representation, collaborators can communicate geometric, semantic and dynamic information about the environment across frames of reference to one another. Existing state-of-the art dense mapping systems provide a good starting point for developing a collaborative mapping system, however, no system currently covers collaborative mapping directly. In this paper, we introduce our approach to dense collaborative map-ping, offering an introduction to the problem, a discussion of the key challenges involved in developing such a system and an analysis of preliminary results.

Item Type:	Book Section
Additional Information:	This paper was presented at 19th Irish Machine Vision and Image Processing conference (IMVIP 2017), 30th Aug - 1st Sep 2017, Maynooth, Co. Kildare, Ireland.
Keywords:	Dense; SLAM; Reconstruction; Mapping; Collaborative;
Academic Unit:	Faculty of Science and Engineering > Computer Science Faculty of Science and Engineering > Research Institutes > Hamilton Institute
Item ID:	12009
Depositing User:	John McDonald
Date Deposited:	06 Dec 2019 12:11
Publisher:	Irish Pattern Recognition & Classification Society
Refereed:	Yes
URI:	Publisher Publisher Organisation
Use Licence:	This item is available under a Creative Commons Attribution Non Commercial Share Alike Licence (CC BY-NC-SA). Details of this licence are available here

Repository Staff Only(login required)

Item control page

Downloads

Origin of downloads