Quantifying and Assessing Model Fidelity for ATR Data Augmentation
Abstract
Approved for Public ReleaseConvolutional neural networks (CNNs) are increasingly employed in remote sensing applications such as synthetic aperture sonar (SAS) where the available sensor imagery may be limited. These networks can be applied for recognition and classification tasks in automated target recognition (ATR) algorithms. Successful training of ATR algorithms, however, generally requires many unique observations of the targets of interest. The increasing fidelity of target and environmental modeling suggests that it may be possible to augment ATR training data sets with additional data that is generated through modeling and simulation. This project will investigate the fidelity that is required of simulated data to be used interchangeably with experimental data for training ATR algorithms.Using precisely controlled in-air acoustic instrumentation, experimental SAS data will be collected on scenes withincreasing complexity. Several environmental and target models will be used to generate complementary simulated data of the same types of scenes. CNNs of varying complexity will then be trained on subsets and combinations of these two data sets at multiple levels of resolution and fidelity. By quantifying the performance of the networks and comparing the mutual information between the experimental and synthetic data, this research will seek to identify the relationships between network architecture, scene complexity, model fidelity, and algorithm performance.
Document Details
- Document Type
- DoD Grant Award
- Publication Date
- Sep 11, 2023
- Source ID
- N000142312846
Entities
People
- Thomas E. Blanford
Organizations
- Office of Naval Research
- United States Navy
- University System of New Hampshire