Canada Spends Logo

Explorez notre analyse du budget 2026

Grant: Discovery Grants Program - Individual

McMaster University

$23,630.00

Emerging applications of machine vision

EF 2011-12

Résumé
Machine vision is a strategically important technology for emerging exciting fields such as robotic-assisted surgery, biometrics (e.g. face recognition), virtual environments and others. Robust visual sensing is required for use with advanced strategies for motion control, sensor fusion, and pattern recognition using new approaches for embedded processing and communications among ""smart"" sensors in networks. Challenges that are common to most applications, to various degrees, are those of illumination, reflections, and occlusions that introduce unpredictability for visual sensing in dynamic environments. Examples are readily found in human-robot interaction and mobile, autonomous robot applications. Reflective surfaces are encountered in robot-assisted surgery (eg. biological materials), in industrial automation (eg. manipulation of flexible sheet metal and glass), in metal machining, and in human face recognition (eg. skin and eyeglasses). The proposed work builds upon recent advances by my group and others in the areas of statistical pattern recognition subspace techniques (also known as ""appearance"" methods). Independent component analysis (ICA), kernel, and support vector machine (SVM) techniques will continue to be used as a basis for novel and efficient processing solutions. Development will also continue with our work on prototypes for distributed control and visual sensor networks that operate in the presence of transport delay, jitter and packet loss. Of specific interest are applications of our prototypes to the difficult ""direct"" visual servo scenario, in which visual feedback alone is used to close a position loop for robotic guidance. This strategy is appropriate when there is no access to positional information (typically from joint angle encoders). Examples include redundant control for safety monitoring in robotic aerospace operations, for machines that are inherently dangerous due to size, and for human-robot cooperative interaction. Machine vision-based control of nano-scale mechanisms and monitoring in microfluidics are intriguing and emerging potential applications of the proposed research.
Programme
Discovery Grants Program - Individual
Bénéficiaire
Emplacement
Ontario, Canada
Type de bénéficiaire
Academia
Type
Grant
Source
NSERC's Awards Data

Tel que publié

Application id
9973-2007
Name nom
Capson, David
Department département
Electrical and Computer Engineering
Organization id
27
Institution établissement
McMaster University
Province en
Ontario
Province fr
Ontario
Country en
CANADA
Country fr
CANADA
Fiscal year exercice financier
2011
Competition year année de concours
2007
Award amount
23630
Program id
RGPIN
Program nane en
Discovery Grants Program - Individual
Program name fr
Programme de subventions à la découverte - individuelles
Group en
Discovery grants programs
Group fr
Programmes de subventions à la découverte
Committee code
335
Committee name en
Electromag. & Electr. Systems (H)
Committee name fr
Électromagn. et syst. électr. (H)
Area of application code
802
Area of application group en
Information and communication services
Area of application group fr
Services d'information et de télécommunications
Area of application en
Information systems and technology
Area of application fr
Systèmes d'information et technologie de l'information
Research subject code
2603
Research subject group en
Robotics
Research subject group fr
Robotique
Research subject en
Computer vision
Research subject fr
Vision artificielle
Partie
5
Nb partie
5
Application title
Emerging applications of machine vision
Keyword
NSERC
Application summary
Machine vision is a strategically important technology for emerging exciting fields such as robotic-assisted surgery, biometrics (e.g. face recognition), virtual environments and others. Robust visual sensing is required for use with advanced strategies for motion control, sensor fusion, and pattern recognition using new approaches for embedded processing and communications among ""smart"" sensors in networks. Challenges that are common to most applications, to various degrees, are those of illumination, reflections, and occlusions that introduce unpredictability for visual sensing in dynamic environments. Examples are readily found in human-robot interaction and mobile, autonomous robot applications. Reflective surfaces are encountered in robot-assisted surgery (eg. biological materials), in industrial automation (eg. manipulation of flexible sheet metal and glass), in metal machining, and in human face recognition (eg. skin and eyeglasses). The proposed work builds upon recent advances by my group and others in the areas of statistical pattern recognition subspace techniques (also known as ""appearance"" methods). Independent component analysis (ICA), kernel, and support vector machine (SVM) techniques will continue to be used as a basis for novel and efficient processing solutions. Development will also continue with our work on prototypes for distributed control and visual sensor networks that operate in the presence of transport delay, jitter and packet loss. Of specific interest are applications of our prototypes to the difficult ""direct"" visual servo scenario, in which visual feedback alone is used to close a position loop for robotic guidance. This strategy is appropriate when there is no access to positional information (typically from joint angle encoders). Examples include redundant control for safety monitoring in robotic aerospace operations, for machines that are inherently dangerous due to size, and for human-robot cooperative interaction. Machine vision-based control of nano-scale mechanisms and monitoring in microfluidics are intriguing and emerging potential applications of the proposed research.