Performance analysis of total least squares methods in three-dimensional motion estimation
DSpace at IIT Bombay
View Archive InfoField | Value | |
Title |
Performance analysis of total least squares methods in three-dimensional motion estimation
|
|
Creator |
CHAUDHURI, SUBHASIS
CHATTERJEE, SHANKAR |
|
Subject |
artificial intelligence
estimation theory matrix algebra parameter estimation pattern recognition picture processing |
|
Description |
An algorithm is presented to obtain the total least squares (TLS) estimates of the motion parameters of an object from range/stereo data or perspective views in a closed form. TLS estimates are suitable when data in both time frames are corrupted by noise, which is an appropriate model for motion analysis in practice. The robustness of different linear least squares methods is analyzed for the estimation of motion parameters against the sensor noise and possible mismatches in establishing object feature point correspondence. As the errors in point correspondence increase, the performance of an ordinary least squares (LS) estimator was found to deteriorate much faster than that of the TLS estimator. The Cramer-Rao lower bound (CRLB) of the error covariance matrix was derived for the TLS model under the assumption of uncorrelated additive Gaussian noise. The CRLB for the TLS model is shown to be always higher than that for the LS model.
|
|
Publisher |
IEEE
|
|
Date |
2008-11-21T10:38:45Z
2011-11-25T12:50:19Z 2011-12-26T13:07:50Z 2011-12-27T05:55:49Z 2008-11-21T10:38:45Z 2011-11-25T12:50:19Z 2011-12-26T13:07:50Z 2011-12-27T05:55:49Z 1991 |
|
Type |
Article
|
|
Identifier |
IEEE Transactions on Robotics and Automation 7(5), 707-14
1042-296X http://dx.doi.org/10.1109/70.97884 http://hdl.handle.net/10054/93 http://dspace.library.iitb.ac.in/xmlui/handle/10054/93 |
|
Language |
en_US
|
|