Grant: Engage Grants Program
Concordia University
$25,000.00
Omnidirectional image tracking for live and accurate augmented reality engineering applications
EF 2012-13
Résumé
Augmented reality (AR) is a visualization method in which virtual objects are aligned with the real world and
the viewer can interact with the virtual objects in real time. Using a variety of 3D modeling, tracking, user
interaction, rendering and display techniques, AR enhances users' immersion by allowing them to view the AR
environment while moving in the real world.
AR has a lot of potential in the world of infrastructure. For instance, it could be used for building site
monitoring. It could also be used as a tool for querying real world objects, for instance to display cadaster info
for houses and maintenance data for hydrants, just by clicking on them whilst on site.
One of the main difficulties in AR is measuring with accuracy the position and orientation of the device used
for augmentation. Any error in the measurement of the camera pose translates into augmentation error. The
camera pose can be estimated using electronic devices (e.g. GPS, orientation sensors), but such devices suffer
from accuracy and drift limitations. Consequently, an increasing number of researchers work with the video
stream captured by the camera to calculate the pose. Those techniques are however limited by the aperture
problem: the camera has a limited width of view, limiting the capacity of the system to estimate the camera
pose with sufficient accuracy, because it does not see ""enough"" of the environment. At the moment, the level
of accuracy for camera pose obtained using single cameras is not sufficient for developing AR systems that
would be used by engineers.
The objective of this project is to develop immersive remote construction site monitoring using an
omnidirectional video camera. More specifically, the main technical problem to be addressed is to develop and
test image feature tracking methods that can work in the spherical context of the omnidirectional video camera.
Programme
Engage Grants Program
Bénéficiaire
Emplacement
Quebec, Canada
Type de bénéficiaire
Academia
Type
Grant
Source
NSERC's Awards Data
Tel que publié
Application id
433995-2012
Name nom
Hammad, Amin
Department département
Concordia Institute for Information Systems Engineering (CIISE)
Organization id
70
Institution établissement
Concordia University
Province en
Québec
Province fr
Québec
Country en
CANADA
Country fr
CANADA
Fiscal year exercice financier
2012
Competition year année de concours
2012
Award amount
25000
Program id
EGP
Program name en
Engage Grants Program
Program name fr
Programme de subventions d'engagement partenariat
Group en
Research partnerships programs
Group fr
Programmes de partenariat
Committee code
1552
Committee name en
Quebec Internal Decision Committee
Committee name fr
Comité de décision interne pour le Québec
Area of application code
1001
Area of application group en
Northern development
Area of application group fr
Développement du nord
Area of application en
Construction, transportation and communications
Area of application fr
Construction, transports et communications
Research subject code
2716
Research subject group en
Information technology
Research subject group fr
Technologie de l'information
Research subject en
Virtual reality and related simulations
Research subject fr
Réalité virtuelle et simulations connexes
Partie
1
Nb partie
1
Application title
Omnidirectional image tracking for live and accurate augmented reality engineering applications
Keyword
NSERC
Application summary
Augmented reality (AR) is a visualization method in which virtual objects are aligned with the real world and
the viewer can interact with the virtual objects in real time. Using a variety of 3D modeling, tracking, user
interaction, rendering and display techniques, AR enhances users' immersion by allowing them to view the AR
environment while moving in the real world.
AR has a lot of potential in the world of infrastructure. For instance, it could be used for building site
monitoring. It could also be used as a tool for querying real world objects, for instance to display cadaster info
for houses and maintenance data for hydrants, just by clicking on them whilst on site.
One of the main difficulties in AR is measuring with accuracy the position and orientation of the device used
for augmentation. Any error in the measurement of the camera pose translates into augmentation error. The
camera pose can be estimated using electronic devices (e.g. GPS, orientation sensors), but such devices suffer
from accuracy and drift limitations. Consequently, an increasing number of researchers work with the video
stream captured by the camera to calculate the pose. Those techniques are however limited by the aperture
problem: the camera has a limited width of view, limiting the capacity of the system to estimate the camera
pose with sufficient accuracy, because it does not see ""enough"" of the environment. At the moment, the level
of accuracy for camera pose obtained using single cameras is not sufficient for developing AR systems that
would be used by engineers.
The objective of this project is to develop immersive remote construction site monitoring using an
omnidirectional video camera. More specifically, the main technical problem to be addressed is to develop and
test image feature tracking methods that can work in the spherical context of the omnidirectional video camera.