Optimizing deep learning classifier performance for low to medium resolution overhead imagery

Jonathan J. Dalrymple; Matthew D. Reisman; Adam G. Francisco; Garrett D. Zans; Taber J. Fisher

doi:10.1117/12.2587102

12 April 2021 Optimizing deep learning classifier performance for low to medium resolution overhead imagery

Jonathan J. Dalrymple, Matthew D. Reisman, Adam G. Francisco, Garrett D. Zans, Taber J. Fisher

Proceedings Volume 11729, Automatic Target Recognition XXXI; 1172906 (2021) https://doi.org/10.1117/12.2587102
Event: SPIE Defense + Commercial Sensing, 2021, Online Only

Abstract

Deep learning-based classification of objects in overhead imagery is a difficult problem to solve due to low to moderate available resolution as well as wide ranges of scale between objects. Traditional machine learning object classification techniques yield sub-optimal results in this scenario, with new techniques developed to optimize performance. Our Lockheed Martin team has developed data pre-processing techniques such as context masking and uniform rotation which improve classifier performance in this application. Additionally, we have demonstrated that shallow classifier models perform at least as well as deeper models in this paradigm, allowing for fast training and inference times.

Conference Presentation

Citation Download Citation

Jonathan J. Dalrymple, Matthew D. Reisman, Adam G. Francisco, Garrett D. Zans, and Taber J. Fisher "Optimizing deep learning classifier performance for low to medium resolution overhead imagery", Proc. SPIE 11729, Automatic Target Recognition XXXI, 1172906 (12 April 2021); https://doi.org/10.1117/12.2587102

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available