Please use this identifier to cite or link to this item: https://doi.org/10.5244/C.19.46
Title: Human posture sequence estimation using two un-calibrated cameras
Authors: Wang, R.
Leow, W.K. 
Issue Date: 2005
Source: Wang, R.,Leow, W.K. (2005). Human posture sequence estimation using two un-calibrated cameras. BMVC 2005 - Proceedings of the British Machine Vision Conference 2005. ScholarBank@NUS Repository. https://doi.org/10.5244/C.19.46
Abstract: 3D Human posture sequence estimation from single or multiple image sequences is essential in many applications, such as vision-based sport coaching and physical rehabilitation. However, 3D posture sequence cannot be accurately estimated from single image sequence due to depth ambiguity and self-occlusion, and pre-calibration is often required when estimating 3D posture sequence from multiple image sequences. In this paper, we present an algorithm to accurately estimate 3D human posture sequence from two un-calibrated image sequences by combining a modified Nonparametric Belief Propagation (mNBP) method with an improved camera self-calibration method. The mNBP estimates posture even when there is partial self-occlusion and when the human model scale is different from that of body image in image sequences. The improved self-calibration guarantees to find the optimal rotation and relative scale between two fixed but un-calibrated scaled orthographic cameras, without a nonlinear optimization process. Quantitative and qualitative experiment results show that the algorithm is able to estimate 3D posture sequence from a pair of un-calibrated image sequences.
Source Title: BMVC 2005 - Proceedings of the British Machine Vision Conference 2005
URI: http://scholarbank.nus.edu.sg/handle/10635/78177
DOI: 10.5244/C.19.46
Appears in Collections:Staff Publications

Show full item record
Files in This Item:
There are no files associated with this item.

SCOPUSTM   
Citations

1
checked on Feb 21, 2018

Page view(s)

19
checked on Feb 24, 2018

Google ScholarTM

Check

Altmetric


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.