Reducing Drift in Parametric Motion Tracking
We develop a class of differential motion trackers that automatically stabilize when in finite domains. Most differ-ential trackers compute motion only relative to one previous frame, accumulating errors indefinitely. We estimate pose changes between a set of past frames, and develop a probabilistic...
Main Authors: | , , |
---|---|
Language: | en_US |
Published: |
2004
|
Online Access: | http://hdl.handle.net/1721.1/6078 |
_version_ | 1826197629461069824 |
---|---|
author | Rahimi, A. Morency, L.-P. Darrell, T. |
author_facet | Rahimi, A. Morency, L.-P. Darrell, T. |
author_sort | Rahimi, A. |
collection | MIT |
description | We develop a class of differential motion trackers that automatically stabilize when in finite domains. Most differ-ential trackers compute motion only relative to one previous frame, accumulating errors indefinitely. We estimate pose changes between a set of past frames, and develop a probabilistic framework for integrating those estimates. We use an approximation to the posterior distribution of pose changes as an uncertainty model for parametric motion in order to help arbitrate the use of multiple base frames. We demonstrate this framework on a simple 2D translational tracker and a 3D, 6-degree of freedom tracker. |
first_indexed | 2024-09-23T10:51:00Z |
id | mit-1721.1/6078 |
institution | Massachusetts Institute of Technology |
language | en_US |
last_indexed | 2024-09-23T10:51:00Z |
publishDate | 2004 |
record_format | dspace |
spelling | mit-1721.1/60782019-04-12T08:28:59Z Reducing Drift in Parametric Motion Tracking Rahimi, A. Morency, L.-P. Darrell, T. We develop a class of differential motion trackers that automatically stabilize when in finite domains. Most differ-ential trackers compute motion only relative to one previous frame, accumulating errors indefinitely. We estimate pose changes between a set of past frames, and develop a probabilistic framework for integrating those estimates. We use an approximation to the posterior distribution of pose changes as an uncertainty model for parametric motion in order to help arbitrate the use of multiple base frames. We demonstrate this framework on a simple 2D translational tracker and a 3D, 6-degree of freedom tracker. 2004-10-04T14:37:42Z 2004-10-04T14:37:42Z 2001-05-07 AIM-2001-008 http://hdl.handle.net/1721.1/6078 en_US AIM-2001-008 8757672 bytes 1663085 bytes application/postscript application/pdf application/postscript application/pdf |
spellingShingle | Rahimi, A. Morency, L.-P. Darrell, T. Reducing Drift in Parametric Motion Tracking |
title | Reducing Drift in Parametric Motion Tracking |
title_full | Reducing Drift in Parametric Motion Tracking |
title_fullStr | Reducing Drift in Parametric Motion Tracking |
title_full_unstemmed | Reducing Drift in Parametric Motion Tracking |
title_short | Reducing Drift in Parametric Motion Tracking |
title_sort | reducing drift in parametric motion tracking |
url | http://hdl.handle.net/1721.1/6078 |
work_keys_str_mv | AT rahimia reducingdriftinparametricmotiontracking AT morencylp reducingdriftinparametricmotiontracking AT darrellt reducingdriftinparametricmotiontracking |