Share Email Print

Proceedings Paper

Open set recognition of aircraft in aerial imagery using synthetic template models
Author(s): Aleksander B. Bapst; Jonathan Tran; Mark W. Koch; Mary M. Moya; Robert Swahn
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

Fast, accurate and robust automatic target recognition (ATR) in optical aerial imagery can provide game-changing advantages to military commanders and personnel. ATR algorithms must reject non-targets with a high degree of confidence in a world with an infinite number of possible input images. Furthermore, they must learn to recognize new targets without requiring massive data collections. Whereas most machine learning algorithms classify data in a closed set manner by mapping inputs to a fixed set of training classes, open set recognizers incorporate constraints that allow for inputs to be labelled as unknown. We have adapted two template-based open set recognizers to use computer generated synthetic images of military aircraft as training data, to provide a baseline for military-grade ATR: (1) a frequentist approach based on probabilistic fusion of extracted image features, and (2) an open set extension to the one-class support vector machine (SVM). These algorithms both use histograms of oriented gradients (HOG) as features as well as artificial augmentation of both real and synthetic image chips to take advantage of minimal training data. Our results show that open set recognizers trained with synthetic data and tested with real data can successfully discriminate real target inputs from non-targets. However, there is still a requirement for some knowledge of the real target in order to calibrate the relationship between synthetic template and target score distributions. We conclude by proposing algorithm modifications that may improve the ability of synthetic data to represent real data.

Paper Details

Date Published: 1 May 2017
PDF: 18 pages
Proc. SPIE 10202, Automatic Target Recognition XXVII, 1020206 (1 May 2017); doi: 10.1117/12.2262150
Show Author Affiliations
Aleksander B. Bapst, Sandia National Labs. (United States)
Jonathan Tran, Sandia National Labs. (United States)
Mark W. Koch, Sandia National Labs. (United States)
Mary M. Moya, Sandia National Labs. (United States)
Robert Swahn, Defense Threat Reduction Agency (United States)

Published in SPIE Proceedings Vol. 10202:
Automatic Target Recognition XXVII
Firooz A. Sadjadi; Abhijit Mahalanobis, Editor(s)

© SPIE. Terms of Use
Back to Top
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?