NASA SBIR 2020-II Solicitation

Proposal Summary

Proposal Information

Proposal Number:
20-2- S5.03-5306
Phase 1 Contract #:
80NSSC20C0572
Subtopic Title:
Accelerating NASA Science and Engineering through the Application of Artificial Intelligence
Proposal Title:
Deep Neural Network Algorithms for Upsampling of Surface Images

Small Business Concern

   
Firm:
          
Physical Sciences, Inc.
          
   
Address:
          
20 New England Business Center , Andover, MA 01810
          
   
Phone:
          
(978) 689-0003                                                                                                                                                                                
          

Principal Investigator:

   
Name:
          
Dr. Kirill Shokhirev
          
   
E-mail:
          
shokhirev@psicorp.com
          
   
Address:
          
20 New England Business Center, MA 01810 - 1077
          
   
Phone:
          
(978) 738-8261                                                                                                                                                                                
          

Business Official:

   
Name:
          
Dr. B. David Green
          
   
E-mail:
          
green@psicorp.com
          
   
Address:
          
20 New England Business Center, MA 01810 - 1077
          
   
Phone:
          
(978) 689-0003                                                                                                                                                                                
          

Summary Details:

   
Estimated Technology Readiness Level (TRL) :                                                                                                                                                          
Begin: 4
End: 6
          
          
     
Technical Abstract (Limit 2000 characters, approximately 200 words):

Physical Sciences Inc. (PSI) proposes to develop the Single Image Super Resolution for Quantitative Analysis (QuantSISR) software suite comprising of state-of-the-art super-resolution (SR) algorithms optimized to reduce errors during subsequent image analysis such as common computer vision tasks (image segmentation, object detection). QuantSISR will be designed to achieve a 50% reduction in edge localization errors while matching pixel-wise accuracy comparable to methods optimized for visual perception quality. The QuantSISR algorithms will improve temporal coverage of data products, such as land cover/land use maps and building footprints.  These objectives are achieved by generating super-resolved visible and hyperspectral images from low-resolution data sets to increase the temporal revisit frequency of existing high resolution datasets. The algorithms are able to generalize to new sensors and regions without any reference imagery, but can also utilize high-resolution reference imagery, when available, to improve accuracy.  This feature can be used during Solar System exploration missions to mitigate mismatch between terrestrial training data sets and the newly acquired data. By leveraging multiple observation geometries, high resolution in situ references can be obtained and used to enhance wide area images acquired at lower spatial resolution. QuantSISR algorithms will be capable of 2x-8x up-sampling and support processing of multispectral and hyperspectral data and the high dynamic range (≥ 16 bit) of modern imagers. QuantSISR software suite will incorporate utilities for parsing and assembling common image data types and image pre- and post-processing to enable seamless integration with existing processing infrastructures. QuantSISR will be packaged to operate on a range of user designated computing platforms, from embedded CPU-GPU systems to computer clusters and cloud computing services.

          
          
     
Potential NASA Applications (Limit 1500 characters, approximately 150 words):

The proposed QuantSISR capability will directly address NASA’s need for more accurate super-resolution of existing and future observations. Potential NASA applications include Moon to Mars (rover navigation, obstacle avoidance); Europa Lander (landing site selection); long-term Earth observations (combining historical low resolution images with currently available high resolution images), such as Surface Biology and Geology (SBG) mission.

          
          
     
Potential Non-NASA Applications (Limit 1500 characters, approximately 150 words):

Non-NASA Commercial Applications include up-sampling of low-resolution images to improve accuracy and/or reduce cost of analyses used for Land Management, Urban Planning, Environmental Monitoring, Transportation and other applications.

          
          
     
Duration:     24
          
          

Form Generated on 05/13/2021 14:41:41