An efficient visual fiducial localisation system

Lightbody, Peter, Hanheide, Marc and Krajnik, Tomas (2017) An efficient visual fiducial localisation system. Applied Computing Review, 17 (3). pp. 28-37. ISSN 1559-6915

Documents
ec4ebaef91e81085404ca74d9f87773b.pdf
[img]
[Download]
[img]
Preview
PDF
ec4ebaef91e81085404ca74d9f87773b.pdf - Whole Document

1MB
Item Type:Article
Item Status:Live Archive

Abstract

With use cases that range from external localisation of single robots or robotic swarms to self-localisation in marker-augmented environments and simplifying perception by tagging objects in a robot's surrounding, fiducial markers have a wide field of application in the robotic world.
We propose a new family of circular markers which allow for both computationally efficient detection, tracking and identification and full 6D position estimation.
At the core of the proposed approach lies the separation of the detection and identification steps, with the former using computationally efficient circular marker detection and the latter utilising an open-ended `necklace encoding', allowing scalability to a large number of individual markers.
While the proposed algorithm achieves similar accuracy to other state-of-the-art methods, its experimental evaluation in realistic conditions demonstrates that it can detect markers from larger distances while being up to two orders of magnitude faster than other state-of-the-art fiducial marker detection methods. In addition, the entire system is available as an open-source package at \url{https://github.com/LCAS/whycon}.

Additional Information:Copyright is held by the authors. This work is based on an earlier work: SAC’17 Proceedings of the 2017 ACM Symposium on Applied Computing, Copyright 2017 ACM 978-1-4503-4486-9. http://dx.doi.org/10. 1145/3019612.3019709
Keywords:real-time object tracking, Object Tracking, Vision for robotics, Tracking, Fiducial Markers, Swarm Robotics, Necklace Code
Subjects:H Engineering > H671 Robotics
G Mathematical and Computer Sciences > G400 Computer Science
G Mathematical and Computer Sciences > G740 Computer Vision
Divisions:College of Science > School of Computer Science
Related URLs:
ID Code:29678
Deposited On:24 Nov 2017 11:07

Repository Staff Only: item control page