Learned Frequency Domain Masks for Training-Size-Robust Sonar Automatic Target Recognition
Abstract
Deep learning has enabled significant improvements in semantic image segmentation, especially in underwater imaging domains like side-scan-sonar (SSS). In this work, we apply deep learning to synthetic aperture sonar (SAS) imagery which has an advantage over traditional SSS in that SAS produces coherent high- and constant-resolution imagery. Despite the successes of deep learning, one drawback is the need for abundant labeled training data to enable success. Such abundant labeled data is not always available as in the case of SAS where collections are expensive and obtaining quality ground truth labels may require diver intervention. To overcome these challenges, we propose a domain-specific deep learning network architecture utilizing a unique property to complex-valued SAS imagery: the ability to resolve angle-of-arrival (AoA) of acoustic returns through $k$-space processing. By sweeping through consecutive incrementally advanced AoA bandpass filters, this technique generates a sequence of images emphasizing angle dependent seafloor scattering and motion from biologics along the seafloor or in the water column.
Document Details
- Document Type
- Technical Report
- Publication Date
- Aug 31, 2022
- Accession Number
- AD1190057
Entities
People
- Issac Gerg
Organizations
- Pennsylvania State University