Grant: Discovery Grants Program - Individual
University of Saskatchewan
$17,000.00
Spectral imaging for crop protection
FY 2010-11
Summary
The objective of the proposed research program is to develop methods for automated interpretation of spectral image data from plants and scenes of plants. This includes determining the structure, species composition, and health of a plant canopy. Spectral images of the scenes are collected using spectral imaging equipment. These instruments provide detailed spectral and spatial information, allowing subtle differences and relationships in pigmentation, structure, and surface characteristics to be observed and used. It is also possible to use light outside of the range visible to people. Based on prior spectral work, this project proposes to use the ultraviolet spectrum in addition to the visible and very-near infrared. This will be a unique contribution to the state of the art in this field, and imaging more generally.
Two particular aspects of interpreting complex biological scenes will be studied: species identification, and using the directional dependencies of reflectance to reconstruct canopy structure. Species identification will be accomplished by developing techniques to quantify definable characteristics about species in ways that do not require direct comparison to other species. Directional dependency effects will be studied using customised equipment that will enable spectral image data to be acquired from multiple angles around a plant while simultaneously scanning a profile of the plant. These data will assist in scene segmentation tasks by recognizing areas with similar orientation, and allowing for some canopy geometry information to be inferred.
The ability to automatically interpret visual information about complex biological scenes has been identified as a priority for specialty crop production. Application examples include vision systems for greenhouse automation, crop scouting (for disease, weeds, insects, and plant health), and reducing agricultural chemical inputs.
Program
Discovery Grants Program - Individual
Recipient
Location
Saskatchewan, Canada
Recipient Type
Academia
Type
Grant
Source
NSERC's Awards Data
As published
Application id
355739-2009
Name nom
Noble, Scott
Department département
Agricultural and Bioresource Engineering
Organization id
16
Institution établissement
University of Saskatchewan
Province en
Saskatchewan
Province fr
Saskatchewan
Country en
CANADA
Country fr
CANADA
Fiscal year exercice financier
2010
Competition year année de concours
2009
Award amount
17000
Program id
RGPIN
Program name 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
1079
Committee name en
Electrical and Computer Engineering
Committee name fr
Génie électrique et de l'informatique
Area of application code
1209
Area of application group en
Advancement of knowledge
Area of application group fr
Avancement des connaissances
Area of application en
Agriculture
Area of application fr
Agriculture
Research subject code
1200
Research subject group en
Agricultural engineering
Research subject group fr
Génie rural
Research subject en
Agricultural engineering
Research subject fr
Génie rural
Partie
2
Nb partie
5
Application title
Spectral imaging for crop protection
Keyword
NSERC
Application summary
The objective of the proposed research program is to develop methods for automated interpretation of spectral image data from plants and scenes of plants. This includes determining the structure, species composition, and health of a plant canopy. Spectral images of the scenes are collected using spectral imaging equipment. These instruments provide detailed spectral and spatial information, allowing subtle differences and relationships in pigmentation, structure, and surface characteristics to be observed and used. It is also possible to use light outside of the range visible to people. Based on prior spectral work, this project proposes to use the ultraviolet spectrum in addition to the visible and very-near infrared. This will be a unique contribution to the state of the art in this field, and imaging more generally.
Two particular aspects of interpreting complex biological scenes will be studied: species identification, and using the directional dependencies of reflectance to reconstruct canopy structure. Species identification will be accomplished by developing techniques to quantify definable characteristics about species in ways that do not require direct comparison to other species. Directional dependency effects will be studied using customised equipment that will enable spectral image data to be acquired from multiple angles around a plant while simultaneously scanning a profile of the plant. These data will assist in scene segmentation tasks by recognizing areas with similar orientation, and allowing for some canopy geometry information to be inferred.
The ability to automatically interpret visual information about complex biological scenes has been identified as a priority for specialty crop production. Application examples include vision systems for greenhouse automation, crop scouting (for disease, weeds, insects, and plant health), and reducing agricultural chemical inputs.