Canada Spends Logo

Explorez notre analyse du budget 2026

Grant: Discovery Grants Program - Individual

University of Victoria

$56,000.00

Emerging Applications of Machine Vision for Sustainable and Connected Environments

EF 2023-24

Résumé
Machine vision and machine learning have matured to the point where they now find application in many sectors of strategic and economic importance to Canada and with the increasing importance of sustainable environments, new research opportunities abound. There is unprecedented interest in using advanced visual sensing in environmental systems. For example, Microsoft's "AI for Earth" program sponsors partnerships to address issues in climate and biodiversity research. Exciting new opportunities are emerging that use artificial vision for monitoring oceans plastics pollution, agricultural and aquaculture systems, new species discovery, behavioural tracking, and others. In addition, inter-connectivity and ubiquitous mobile computing platforms have enabled machine vision and machine learning to extend to diverse fields such as robotic-assisted surgery, biometrics (e.g. face recognition) and gesture recognition. Advances rely on 3D visual sensing methodologies coupled with innovative control strategies, multi-sensor fusion and robust pattern recognition. New approaches are also vital for embedding advanced capabilities into hand held computing platforms to exploit multi-core and distributed processing resources (such as mobile GPUs) and "smart" sensor networks. But all of these examples share common technical challenges associated with illumination, shadows and occlusions that introduce unpredictable conditions for visual sensing in natural and dynamic environments. The long term objectives of this research program include the development of new approaches for visual sensing applied to problems for sustainability of our natural environmental and to train HQP in contemporary methodologies in machine vision and machine learning. With the increasing need of skilled HQP, there will be immediate impact with Canadian employers. The near-term objectives of this research program are to develop novel and robust methods for visual measurements that are robust to unpredictable reflection, random occlusion, cluttered environments and variable illumination. Examples include (a) environments in which lighting changes over a large dynamic range due to variable sunlight, cloud movement and reflections (b) augmented reality or tele-robotic applications in unstructured environments and (c) imaging of deformable and reflective surfaces. The near-term objectives of this research program include a focus on the development of new sensory test beds for visual classification of household plastic bottles for recycling and tracking of hand gestures on mobile platforms. New algorithms will be developed that are designed to exploit the capabilities of FPGA and advanced mobile GPU architectures. Multi-modal image registration using deep-learning techniques are being applied to environmental systems that include natural ocean-floor and mountain landscape imagery.
Programme
Discovery Grants Program - Individual
Emplacement
British Columbia, Canada
Type de bénéficiaire
Academia
Type
Grant
Source
NSERC's Awards Data

Tel que publié

Application id
RGPIN-2019-04787
Name nom
Capson, David
Department département
Electrical and Computer Engineering
Organization id
7
Institution établissement
University of Victoria
Province en
British Columbia
Province fr
Colombie-Britannique
Country en
CANADA
Country fr
CANADA
Fiscal year exercice financier
2023
Competition year année de concours
2019
Award amount
56000
Program id
RGPIN
Program name en
Discovery Grants Program - Individual
Program name fr
Programme de subventions à la découverte - individuelles
Group en
DISCOVERY RESEARCH
Group fr
RECHERCHE AXÉE SUR LA DÉCOUVERTE
Committee code
1510
Committee name en
Electrical and Computer Engineering
Committee name fr
Génie électrique et informatique
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
9999
Research subject group en
Not available
Research subject group fr
Not available
Research subject en
Non disponible
Research subject fr
Non disponible
Application title
Emerging Applications of Machine Vision for Sustainable and Connected Environments
Keyword
computational vision structures; machine vision; smart sensing; sustainable sensing; virtual environments
Application summary
Machine vision and machine learning have matured to the point where they now find application in many sectors of strategic and economic importance to Canada and with the increasing importance of sustainable environments, new research opportunities abound. There is unprecedented interest in using advanced visual sensing in environmental systems. For example, Microsoft's "AI for Earth" program sponsors partnerships to address issues in climate and biodiversity research. Exciting new opportunities are emerging that use artificial vision for monitoring oceans plastics pollution, agricultural and aquaculture systems, new species discovery, behavioural tracking, and others. In addition, inter-connectivity and ubiquitous mobile computing platforms have enabled machine vision and machine learning to extend to diverse fields such as robotic-assisted surgery, biometrics (e.g. face recognition) and gesture recognition. Advances rely on 3D visual sensing methodologies coupled with innovative control strategies, multi-sensor fusion and robust pattern recognition. New approaches are also vital for embedding advanced capabilities into hand held computing platforms to exploit multi-core and distributed processing resources (such as mobile GPUs) and "smart" sensor networks. But all of these examples share common technical challenges associated with illumination, shadows and occlusions that introduce unpredictable conditions for visual sensing in natural and dynamic environments. The long term objectives of this research program include the development of new approaches for visual sensing applied to problems for sustainability of our natural environmental and to train HQP in contemporary methodologies in machine vision and machine learning. With the increasing need of skilled HQP, there will be immediate impact with Canadian employers. The near-term objectives of this research program are to develop novel and robust methods for visual measurements that are robust to unpredictable reflection, random occlusion, cluttered environments and variable illumination. Examples include (a) environments in which lighting changes over a large dynamic range due to variable sunlight, cloud movement and reflections (b) augmented reality or tele-robotic applications in unstructured environments and (c) imaging of deformable and reflective surfaces. The near-term objectives of this research program include a focus on the development of new sensory test beds for visual classification of household plastic bottles for recycling and tracking of hand gestures on mobile platforms. New algorithms will be developed that are designed to exploit the capabilities of FPGA and advanced mobile GPU architectures. Multi-modal image registration using deep-learning techniques are being applied to environmental systems that include natural ocean-floor and mountain landscape imagery.