Document Type

Article

Publication Date

2013

Journal or Book Title

Lecture Notes in Computer Science

Volume

8022

First Page

281

Last Page

290

DOI

10.1007/978-3-642-39420-1_30

Abstract

We introduce a natural feature tracking approach that facilitates the tracking of rigid objects for an on-site assembly assistance system. The tracking system must track multiple circuit boards without added fiducial markers, and they are manipulated by the user. We use a common SIFT feature matching detector enhanced with a probability search. This search estimates how likely a set of query descriptors belongs to a particular object. The method was realized and tested. The results show that the probability search enhanced the identification of different circuit boards.

Comments

This is a manuscript of an article from Lecture Notes in Computer Science 8022 (2013): 281, doi:10.1007/978-3-642-39420-1_30. Posted with permission. The final publication is available at Springer via http://dx.doi.org/10.1007/978-3-642-39420-1_30.

Copyright Owner

Oliver, et al.

Language

en

File Format

application/pdf

Share

COinS