- Library Home /
- Search Collections /
- Open Collections /
- Browse Collections /
- UBC Theses and Dissertations /
- Argo Project: Machine vision based motion capture for...
Open Collections
UBC Theses and Dissertations
UBC Theses and Dissertations
Argo Project: Machine vision based motion capture for tracking the trajectory of the pose of a mobile rigid body Liggins, Geoffrey Allan
Abstract
The objective of the Argo Project is to develop a tool that will track in real-time the motion of unconstrained, self-propelled, model ships in seakeeping tests done in towing tanks and manoeu-vring basins. To meet the unconstrained requirement, the tracking system must be non- contact and can not interfere with the operation or motion of the model ship. An additional operating requirement is that the sensor must cover an area in excess of thirty square metres. An optical based sensor was selected as it satisfied these constraints. Tracking the motion of the model ship is achieved with a predictive, extended Kalman filter (EKF), using feature point extraction from multiple synchronized images. The EKF is used because it can readily integrate and filter multiple noisy data sets. As well, it can generate an estimate of the pose, namely the position and orientation, of the model ship relative to the reference frame of the test tank. While this project is focused on ship tracking there are many other applications for a system of this kind. TM The system under development makes use of the Qualisys camera and video processor hardware that extract image feature points and return them to a host computer. The incoming image TM feature points are then fed into tracking software developed in MATLAB . The tracking software uses estimates of the image to do feature point correspondence and sorts the incoming data vector into the expected order. The sorted data vector is then used as the input vector for the EKF which computes the photogrammetric equations and computes the state vector for the pose of the mobile object being tracked. This work is being undertaken at the University of British Columbia (UBC), Deparment of Mechanical Engineering, Maritime Engineering and Naval Architecture Research Laboratory. The organizaitons that assisted in this research effort are the Centre for Cold Ocean Resources Engineering, Intelligent Systems Group
Item Metadata
Title |
Argo Project: Machine vision based motion capture for tracking the trajectory of the pose of a mobile rigid body
|
Creator | |
Publisher |
University of British Columbia
|
Date Issued |
1998
|
Description |
The objective of the Argo Project is to develop a tool that will track in real-time the motion of
unconstrained, self-propelled, model ships in seakeeping tests done in towing tanks and manoeu-vring
basins. To meet the unconstrained requirement, the tracking system must be non- contact
and can not interfere with the operation or motion of the model ship. An additional operating requirement
is that the sensor must cover an area in excess of thirty square metres. An optical based
sensor was selected as it satisfied these constraints.
Tracking the motion of the model ship is achieved with a predictive, extended Kalman filter
(EKF), using feature point extraction from multiple synchronized images. The EKF is used because
it can readily integrate and filter multiple noisy data sets. As well, it can generate an estimate
of the pose, namely the position and orientation, of the model ship relative to the reference frame
of the test tank. While this project is focused on ship tracking there are many other applications
for a system of this kind.
TM
The system under development makes use of the Qualisys camera and video processor hardware
that extract image feature points and return them to a host computer. The incoming image
TM
feature points are then fed into tracking software developed in MATLAB . The tracking software
uses estimates of the image to do feature point correspondence and sorts the incoming data vector
into the expected order. The sorted data vector is then used as the input vector for the EKF which
computes the photogrammetric equations and computes the state vector for the pose of the mobile
object being tracked.
This work is being undertaken at the University of British Columbia (UBC), Deparment of Mechanical
Engineering, Maritime Engineering and Naval Architecture Research Laboratory. The
organizaitons that assisted in this research effort are the Centre for Cold Ocean Resources Engineering,
Intelligent Systems Group
|
Extent |
8336710 bytes
|
Genre | |
Type | |
File Format |
application/pdf
|
Language |
eng
|
Date Available |
2009-05-19
|
Provider |
Vancouver : University of British Columbia Library
|
Rights |
For non-commercial purposes only, such as research, private study and education. Additional conditions apply, see Terms of Use https://open.library.ubc.ca/terms_of_use.
|
DOI |
10.14288/1.0080905
|
URI | |
Degree | |
Program | |
Affiliation | |
Degree Grantor |
University of British Columbia
|
Graduation Date |
1998-05
|
Campus | |
Scholarly Level |
Graduate
|
Aggregated Source Repository |
DSpace
|
Item Media
Item Citations and Data
Rights
For non-commercial purposes only, such as research, private study and education. Additional conditions apply, see Terms of Use https://open.library.ubc.ca/terms_of_use.