Grant: Engage Grants Program
Université de Sherbrooke
$25,000.00
Development of deep segmentation methods applied to satellite imagery
FY 2017-18
Summary
In collaboration with UrtheCast inc., the goal of this project is to explore the concrete usability of deepconvolutional neural networks in the field of satellite imagery. Since this project spans over a short period oftime (only 6 months) we will focus on image segmentation, a topic at the core of the research activities of pr.Jodoin and a glaring issue for UrtheCast. As such, we look forward to answer the following four questions:1) Which state-of-the-art network configuration works best and what is its accuracy compared to thenone-deep-learning solutions currently deployed by UrtheCast?2) How many manually annotated satellite images are required to properly train a convolutional neuralnetwork? Also, does weakly annotated data can be used to increase the accuracy of a network?3) How can very large satellite images (from 2,000 x 2,000 to 6,000 x 6,000 pixels) be processed (both attraining and at test time) on a single 12 Gb GPU?4) Can a model trained on a RGB dataset be transferred to a multispectral dataset as well as data from theUrtheCast satellites?Since deep segmentation models are new to the world of remote sensing, this project is fundamentallyimportant both for UrtheCast and the Canadian society as a whole. With its ""UrtheDaily(TM)"" project,UrtheCast is about to deploy a constellation of satellites which will acquire an unprecedented number ofimages that no one can manually analyse. This project will thus provide the company with the tools forprocessing those images. The same models could also be used to process data acquire by other Canadiansatellites such as RadarSat2 and SCISAT.
Program
Engage Grants Program
Recipient
Location
Quebec, Canada
Recipient Type
Academia
Type
Grant
Source
NSERC's Awards Data
As published
Application id
521746-2017
Name nom
Jodoin, PierreMarc
Department département
Informatique
Organization id
68
Institution établissement
Université de Sherbrooke
Province en
Québec
Province fr
Québec
Country en
CANADA
Country fr
CANADA
Fiscal year exercice financier
2017
Competition year année de concours
2017
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
703
Area of application group en
Transportation systems and services
Area of application group fr
Services et systèmes de transport
Area of application en
Aerospace
Area of application fr
Aérospatial
Research subject code
2800
Research subject group en
Artificial intelligence
Research subject group fr
Intelligence artificielle
Research subject en
Artificial intelligence (computer vision, use2603)
Research subject fr
Intelligence artificielle (vision artificielle, utiliser 2603)
Partie
1
Nb partie
1
Application title
Development of deep segmentation methods applied to satellite imagery
Keyword
NSERC
Application summary
In collaboration with UrtheCast inc., the goal of this project is to explore the concrete usability of deepconvolutional neural networks in the field of satellite imagery. Since this project spans over a short period oftime (only 6 months) we will focus on image segmentation, a topic at the core of the research activities of pr.Jodoin and a glaring issue for UrtheCast. As such, we look forward to answer the following four questions:1) Which state-of-the-art network configuration works best and what is its accuracy compared to thenone-deep-learning solutions currently deployed by UrtheCast?2) How many manually annotated satellite images are required to properly train a convolutional neuralnetwork? Also, does weakly annotated data can be used to increase the accuracy of a network?3) How can very large satellite images (from 2,000 x 2,000 to 6,000 x 6,000 pixels) be processed (both attraining and at test time) on a single 12 Gb GPU?4) Can a model trained on a RGB dataset be transferred to a multispectral dataset as well as data from theUrtheCast satellites?Since deep segmentation models are new to the world of remote sensing, this project is fundamentallyimportant both for UrtheCast and the Canadian society as a whole. With its ""UrtheDaily(TM)"" project,UrtheCast is about to deploy a constellation of satellites which will acquire an unprecedented number ofimages that no one can manually analyse. This project will thus provide the company with the tools forprocessing those images. The same models could also be used to process data acquire by other Canadiansatellites such as RadarSat2 and SCISAT.