End-to-End ATR Leveraging Deep Learning

Matthew P. Masarik (), Chris Kreucher (), Kirk Weeks () and Kyle Simpson ()
Additional contact information
Matthew P. Masarik: KBR
Chris Kreucher: KBR
Kirk Weeks: Signature Research, Inc.
Kyle Simpson: Signature Research, Inc.

A chapter in Synthetic Aperture Radar (SAR) Data Applications, 2022, pp 1-23 from Springer

Abstract: Abstract Synthetic aperture radar (SAR) systems are widely used for intelligence, surveillance, and reconnaissance purposes. However, unlike electro-optical (EO) images, SAR images are not easily interpreted and therefore have historically required a trained analyst to extract useful information from images. At the same time, the number of high-resolution SAR systems and the amount of data they generate are rapidly increasing, which has resulted in a shortage of analysts available to interpret this vast amount of SAR data. Therefore, there is a significant need for efficient and reliable automatic target recognition (ATR) algorithms that can ingest a SAR image, find all the objects of interest in the image, classify these objects, and output properties of the objects (location, type, orientation, etc.). This chapter lays out the required steps in any approach for performing these functions and describes a suite of deep learning (DL) algorithms that perform this end-to-end SAR ATR. One novel feature of our method is that we rely on only synthetically generated training data, which avoids some of the main pitfalls of other DL approaches to this problem.

Date: 2022
References: Add references at CitEc
Citations:

There are no downloads for this item, see the EconPapers FAQ for hints about obtaining it.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:spochp:978-3-031-21225-3_1

Ordering information: This item can be ordered from
http://www.springer.com/9783031212253

DOI: 10.1007/978-3-031-21225-3_1

Access Statistics for this chapter

More chapters in Springer Optimization and Its Applications from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().