Camera-less articulated trajectory reconstruction

Zhu, Yingying, Valmadre, Jack and Lucey, Simon (2012). Camera-less articulated trajectory reconstruction. In: 2012 21st International Conference on Pattern Recognition (ICPR 2012). Proceedings. ICPR 2012: 21st International Conference on Pattern Recognition, Tsukuba, Japan, (841-844). 11-15 November, 2012.

Attached Files (Some files may be inaccessible until you login with your UQ eSpace credentials)
Name Description MIMEType Size Downloads
Author Zhu, Yingying
Valmadre, Jack
Lucey, Simon
Title of paper Camera-less articulated trajectory reconstruction
Conference name ICPR 2012: 21st International Conference on Pattern Recognition
Conference location Tsukuba, Japan
Conference dates 11-15 November, 2012
Proceedings title 2012 21st International Conference on Pattern Recognition (ICPR 2012). Proceedings   Check publisher's open access policy
Journal name International Conference on Pattern Recognition   Check publisher's open access policy
Place of Publication Washington, DC, United States
Publisher I E E E Computer Society
Publication Year 2012
Sub-type Fully published paper
ISBN 9781467322164
ISSN 1051-4651
Start page 841
End page 844
Total pages 4
Language eng
Formatted Abstract/Summary
In this paper, we address the problem of reconstructing 3D trajectories given only 2D point projection trajectories of an articulated structure. Hitherto, most applications of articulated trajectory reconstruction require: (i) relative lengths, and (ii) camera motion. We propose a novel extension that allows us to in many circumstances circumvent these limitations. Of particular note is our characterisation theoretically and demonstration empirically how agnostic one be to camera motion when using a DCT basis. Practical reconstructions of non-human articulated structures are depicted (e.g. koala, sea snake, tasmanian tiger) where articulated lengths and camera motion are unknown.
Subjects 1707 Computer Vision and Pattern Recognition
Q-Index Code E1
Q-Index Status Provisional Code
Institutional Status UQ

Version Filter Type
Citation counts: Scopus Citation Count Cited 3 times in Scopus Article | Citations
Google Scholar Search Google Scholar
Created: Thu, 28 Nov 2013, 22:51:38 EST by System User on behalf of School of Information Technol and Elec Engineering