An Adaptive Thresholding Algorithm for the Augmented Reality Toolkit

By Thomas Pintaric

Abstract

It is well known that fixed global thresholds have adverse effects on the reliability of marker-based optical trackers under non-uniform lighting conditions. Mobile Augmented Reality applications, by their very nature, demand a certain level of robustness against varying external illumination from visual tracking algorithms. Currently, ARToolKit depends on fixed-threshold image-binarization in order to detect candidate fiducials for further processing. In an effort to minimize tracking failure due to uniform shadows and reflections off a marker surface, we propose a fast algorithm for selecting adaptive threshold values, based on the arithmetic mean of pixel intensities over a region-of-interest around candidate fiducials.

Reference

T. Pintaric: "An Adaptive Thresholding Algorithm for the Augmented Reality Toolkit"; in: "Proceedings of the Second IEEE International Augmented Reality Toolkit Workshop", IEEE Computer Society Press, Tokyo, Japan, 2003.

BibTeX

@inproceedings{TUW-138108,     author = {Pintaric, Thomas},     title = {An Adaptive Thresholding Algorithm for the Augmented Reality Toolkit},     booktitle = {Proceedings of the Second IEEE International Augmented Reality Toolkit Workshop},     year = {2003},     publisher = {IEEE Computer Society Press},     address = {Tokyo, Japan},     keywords = {ARToolKit, Adaptive Thresholding} } Click into the text area and press Ctrl+A/Ctrl+C or ⌘+A/⌘+C to copy the BibTeX into your clipboard… or download the BibTeX.