Grant: Engage Grants Program
York University
$24,950.00
Robotic navigation and mapping using omni-directional camera
FY 2013-14
Summary
The aim of the project is to use omni-directional images for robotic navigation and 3D mapping of the indoorenvironments. VitualMe, CrossWing's Inc experimental robotic platform, will be used as a personal robotcapable of autonomous task planning. Therefore, autonomous navigation is a fundamental functionalrequirement as it allows the robot to determine its location in space and its path to a specified destination. Therobot is equipped with a parabolic convex mirror dome that provides an omni-directional view of theenvironment. The images are formed by capturing the reflection of the objects from the mirror surface from avideo camera directly beneath the mirror dome. The omni-directional camera sensor model and the calibrationparameters of the optical system will be developed based on the geometry between object space, mirror domeand camera image. The omni-directional camera multi-view overlapping images are used to develop themathematical model for determining the trajectory of the omni-directional camera based on tracking commonfeatures between image frames. The 3D mapping (object structures) will be generated based on a shape frommotion approach using photogrammetric incremental bundle adjustment. The developed algorithms are to betested and validated in a controlled environment including comparisons with conventional camera systems(e.g., stereo-vision system).
Program
Engage Grants Program
Recipient
Location
Ontario, Canada
Recipient Type
Academia
Type
Grant
Source
NSERC's Awards Data
As published
Application id
449584-2013
Name nom
Armenakis, (Constadinos)Costas
Department département
Earth and Space Science and Engineering
Organization id
38
Institution établissement
York University
Province en
Ontario
Province fr
Ontario
Country en
CANADA
Country fr
CANADA
Fiscal year exercice financier
2013
Competition year année de concours
2013
Award amount
24950
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
1553
Committee name en
Ontario Internal Decision Committee
Committee name fr
Comité de décision interne pour l'Ontario
Area of application code
1207
Area of application group en
Advancement of knowledge
Area of application group fr
Avancement des connaissances
Area of application en
Information, computer and communication technologies
Area of application fr
Technologie de l'information, des ordinateurs et des réseaux de communications
Research subject code
4101
Research subject group en
Geographical information
Research subject group fr
Information géographique
Research subject en
Cartography and geomatics
Research subject fr
Cartographie et géomatique
Partie
1
Nb partie
1
Application title
Robotic navigation and mapping using omni-directional camera
Keyword
NSERC
Application summary
The aim of the project is to use omni-directional images for robotic navigation and 3D mapping of the indoorenvironments. VitualMe, CrossWing's Inc experimental robotic platform, will be used as a personal robotcapable of autonomous task planning. Therefore, autonomous navigation is a fundamental functionalrequirement as it allows the robot to determine its location in space and its path to a specified destination. Therobot is equipped with a parabolic convex mirror dome that provides an omni-directional view of theenvironment. The images are formed by capturing the reflection of the objects from the mirror surface from avideo camera directly beneath the mirror dome. The omni-directional camera sensor model and the calibrationparameters of the optical system will be developed based on the geometry between object space, mirror domeand camera image. The omni-directional camera multi-view overlapping images are used to develop themathematical model for determining the trajectory of the omni-directional camera based on tracking commonfeatures between image frames. The 3D mapping (object structures) will be generated based on a shape frommotion approach using photogrammetric incremental bundle adjustment. The developed algorithms are to betested and validated in a controlled environment including comparisons with conventional camera systems(e.g., stereo-vision system).