Share Email Print
cover

Proceedings Paper

Neural net algorithm for target ID trained on simulated data
Author(s): Christopher L. Howell; Kimberly Manser; Jeffrey Olson
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

Simulation-based training for target acquisition algorithms is an important goal for reducing the cost and risk associated with live data collections. To this end, the US Army Night Vision and Electronic Sensors Directorate (NVESD) has developed high-fidelity virtual scenes of terrains and targets using the DIRSIG in pursuit of a virtual DRI (detect, recognize, identify) capability. In this study, the NVESD has developed a neural network (NN) algorithm that can be trained on simulated data to classify targets of interest when presented with real data. This paper discusses the classification performance of a NN algorithm and the potential impact training with simulated data has on algorithm performance.

Paper Details

Date Published: 26 April 2018
PDF: 7 pages
Proc. SPIE 10625, Infrared Imaging Systems: Design, Analysis, Modeling, and Testing XXIX, 106250Q (26 April 2018); doi: 10.1117/12.2305660
Show Author Affiliations
Christopher L. Howell, U.S. Army Night Vision & Electronic Sensors Directorate (United States)
Kimberly Manser, U.S. Army Night Vision & Electronic Sensors Directorate (United States)
Jeffrey Olson, U.S. Army Night Vision & Electronic Sensors Directorate (United States)


Published in SPIE Proceedings Vol. 10625:
Infrared Imaging Systems: Design, Analysis, Modeling, and Testing XXIX
Gerald C. Holst; Keith A. Krapels, Editor(s)

© SPIE. Terms of Use
Back to Top