Sciweavers

Share
PERCOM
2006
ACM

Analysing fundamental properties of marker-based vision system designs

9 years 11 months ago
Analysing fundamental properties of marker-based vision system designs
This paper investigates fundamental properties of Marker-based Vision (MBV) systems. We present a theoretical analysis of the performance of basic tag designs which is extended through simulation to investigate the effects of different processing algorithms. Real-world data are processed and related to the simulated results. Image processing is performed using Cantag, an open source software toolkit for building Marker-based Vision (MBV) systems that can identify and accurately locate printed markers in three dimensions. Cantag supports multiple fiducial shapes, payload types, data sizes and image processing algorithms in one framework. This paper explores the design space of tags within the Cantag system, and describes the design parameters and performance characteristics which an application writer can use to select the best tag system for any given scenario. Key words: Computer Vision, Fiducial Tag Design
Andrew C. Rice, Robert K. Harle, Alastair R. Beres
Added 24 Dec 2009
Updated 24 Dec 2009
Type Conference
Year 2006
Where PERCOM
Authors Andrew C. Rice, Robert K. Harle, Alastair R. Beresford
Comments (0)
books