Synthetic Aperture Radar Image Recognition of Armored Vehicles

Authors

Christopher Szul [*], Air Force Institute of Technology
Torrey J. Wagner, Air Force Institute of TechnologyFollow
Brent T. Langhals, Air Force Institute of TechnologyFollow

Document Type

Conference Proceeding

Publication Date

6-2021

Abstract

Synthetic Aperture Radar (SAR) imagery is not affected by weather and allows for day-and-night observations, however it can be difficult to interpret. This work applies classical and neural network machine learning techniques to perform image classification of SAR imagery. The Moving and Stationary Target Acquisition and Recognition dataset from the Air Force Research Laboratory was used, which contained 2,987 total observations of the BMP-2, BTR-70, and T-72 vehicles. Using a 75%/25% train/test split, the classical model achieved an average multi-class image recognition accuracy of 70%, while a convolutional neural network was able to achieve a 97% accuracy with lower model complexity than exists in the literature. Automated target recognition using SAR imagery can further improve situational awareness for blue forces.

Comments

The authors declare this is a work of the U.S. Government and is not subject to copyright protections in the United States.

Source Publication

89th Military Operations Research Society Symposium, Virtual

Recommended Citation

Szul, Christopher [*]; Wagner, Torrey J.; and Langhals, Brent T., "Synthetic Aperture Radar Image Recognition of Armored Vehicles" (2021). Faculty Publications. 1409.
https://scholar.afit.edu/facpub/1409