Evaluation of augmented training datasets

Keyanna N. Ryan; Bassam N. Bahhur; Mark Jeiran; Bryan I. Vogel

doi:10.1117/12.2587177

12 April 2021 Evaluation of augmented training datasets

Keyanna N. Ryan, Bassam N. Bahhur, Mark Jeiran, Bryan I. Vogel

Proceedings Volume 11740, Infrared Imaging Systems: Design, Analysis, Modeling, and Testing XXXII; 117400K (2021) https://doi.org/10.1117/12.2587177
Event: SPIE Defense + Commercial Sensing, 2021, Online Only

Abstract

Large amounts of labelled imagery are needed to sufficiently train Deep Neural Network (DNN) based classification algorithms. In many cases, collecting an adequate training dataset requires excessive amounts of time and money. The limited data problem is exacerbated when military-relevant imagery requirements are imposed. This often requires imagery collected in the infrared (IR) band, as well as, imagery of military-relevant targets; adding difficulty due to scarcity of sensors, targets, and personnel with the ability to capture the data. To mitigate these types of problems, this study evaluates the effectiveness of synthetic data when aided with small amounts of real data for training DNN based classifier algorithms. This study analyzes the efficacy of the YOLOv3 classifier algorithm at detecting common household objects after training on synthetic data created through an image chipping and insertion method. A set of image chips are created by extracting objects from a green screen background which are then used to generate synthetic training examples by pasting them on a variety of new backgrounds. The impact of background variety and addition of small amounts of real data on trained algorithm performance is analyzed.

Conference Presentation

Citation Download Citation

Keyanna N. Ryan, Bassam N. Bahhur, Mark Jeiran, and Bryan I. Vogel "Evaluation of augmented training datasets", Proc. SPIE 11740, Infrared Imaging Systems: Design, Analysis, Modeling, and Testing XXXII, 117400K (12 April 2021); https://doi.org/10.1117/12.2587177

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