Learning Robust Representations for Automatic Target Recognition
Goodwin, Justin A., Brown, Olivia M., Killian, Taylor W., Son, Sung-Hyun
Radio frequency (RF) sensors are used alongside other sensing modalities to provide rich representations of the world. Given the high variability of complex-valued target responses, RF systems are susceptible to attacks masking true target characteristics from accurate identification. In this work, we evaluate different techniques for building robust classification architectures exploiting learned physical structure in received synthetic aperture radar signals of simulated 3D targets.
Nov-26-2018
- Country:
- North America > United States
- California (0.14)
- Massachusetts > Middlesex County (0.14)
- North America > United States
- Genre:
- Research Report (0.64)
- Industry:
- Government (0.47)
- Leisure & Entertainment (0.34)
- Media > Radio (0.34)
- Technology: