Skip to main content
idi
Toggle navigation
0
You have 0 notifications
Site Visitor
Site Visitor
New To Inknowvation.com?
Register now to get an access to proprietary SBIR-STTR databases!
Registration is fast and free - start your access to business-actionable information today!
Login
Site Register
SBIR-STTR Award
You are here:
Home
Search Databases
Search SBIR-STTR Awards
SBIR-STTR Award
5
Super Resolution of Satellite Imagery using Multi-Sensor Fusion
Award last edited on: 3/8/2024
Sponsored Program
SBIR
Awarding Agency
DOD : NGA
Total Award Amount
$999,984
Award Phase
2
Solicitation Topic Code
NGA172-005
Principal Investigator
Eric Smith
Company Information
Kitware Inc
1712 Route 9 Suite 300
Clifton Park, NY 12065
(518) 371-3971
kitware@kitware.com
www.kitware.com
Location:
Multiple
Congr. District:
20
County:
Saratoga
Phase I
Contract Number:
2019
Start Date:
----
Completed:
5/29/2019
Phase I year
2019
Phase I Amount
$1
Direct to Phase II
Phase II
Contract Number:
N/A
Start Date:
6/2/2021
Completed:
5/29/2019
Phase II year
2019
(last award dollars: 1709927874)
Phase II Amount
$999,983
The commercial small satellite provider Planet is expanding towards global coverage at a daily revisit rate at the cost of lower resolution imagery than satellite providers like DigitalGlobe. The lower resolution diminishes the effectiveness of Planet in many surveillance applications that would greatly benefit from its coverage and revisit rate. We therefore propose a single image super resolution algorithm that increases Planets resolution by leveraging the large archive of DigitalGlobe imagery. Our unique approach splits the problem into two convolutional neural networks: modality transfer and super resolution. The modality transfer network learns to map Planet imagery to match DigitalGlobe appearance by training on registered pairs of Planet and downsampled DigitalGlobe. The modality transferred image is then super resolved by a single image super resolution network trained unsupervised on DigitalGlobe imagery. We combine these networks into a single network for maximum benefit. Our approach also explores the ability to synthesize multiple super resolved hypotheses of an object and retrieve similar examples from the training set to support each result and lend confidence to the synthesized details. The algorithm will integrate into Kitwares VIGLANT system to provide a prototype for analysts use.
×
Login to your account
Mail sent successfully.
Enter any username and password.
Username
Password
Remember me
Login
Forgot your username?
Click here for assistance
Forgot your password?
Request new password
Don't have an account?
Sign up
Forgot username?
Mail sent successfully.
Enter username and password.
Please enter email address that is associated with your account.
Back
Submit
Still Need Help?
If you need further assistance, send us an
e-mail
and we will assist you in resetting your account.
Forgot password?
Mail sent successfully.
Enter username and password.
Please enter email address that is associated with your account.
Back
Submit
Still Need Help?
If you need further assistance, send us an
e-mail
and we will assist you in resetting your account.