DATA AUGMENTATION FOR SYNTHETIC APERTURE RADAR USING ALPHA BLENDING AND DEEP LAYER TRAINING
Loading...
Authors
Denton, Alexander W.
Subjects
artificial intelligence
AI
machine learning
ML
convolutional neural network
CNN
data augmentation
AConvNet
SAMPLE
MSTAR
RADAR
synthetic aperture radar (SAR)
alpha blending
low-resolution
wide area search
background
tip-and-cue
field of view
FOV
feature detection
object detection
target detection
object proposal
target proposal
synthetic dataset
swath
area search
discovery
patch
chip
AI
machine learning
ML
convolutional neural network
CNN
data augmentation
AConvNet
SAMPLE
MSTAR
RADAR
synthetic aperture radar (SAR)
alpha blending
low-resolution
wide area search
background
tip-and-cue
field of view
FOV
feature detection
object detection
target detection
object proposal
target proposal
synthetic dataset
swath
area search
discovery
patch
chip
Advisors
Agrawal, Brij N.
Garren, David A.
Date of Issue
2023-03
Date
Publisher
Monterey, CA; Naval Postgraduate School
Language
Abstract
Human-based object detection in synthetic aperture RADAR (SAR) imagery is complex and technical, laboriously slow but time critical—the perfect application for machine learning (ML). Training an ML network for object detection requires very large image datasets with imbedded objects that are accurately and precisely labeled. Unfortunately, no such SAR datasets exist. Therefore, this paper proposes a method to synthesize wide field of view (FOV) SAR images by combining two existing datasets: SAMPLE, which is composed of both real and synthetic single-object chips, and MSTAR Clutter, which is composed of real wide-FOV SAR images. Synthetic objects are extracted from SAMPLE using threshold-based segmentation before being alpha-blended onto patches from MSTAR Clutter. To validate the novel synthesis method, individual object chips are created and classified using a simple convolutional neural network (CNN); testing is performed against the measured SAMPLE subset. A novel technique is also developed to investigate training activity in deep layers. The proposed data augmentation technique produces a 17% increase in the accuracy of measured SAR image classification. This improvement shows that any residual artifacts from segmentation and blending do not negatively affect ML, which is promising for future use in wide-area SAR synthesis.
Type
Thesis
Description
Series/Report No
Department
Space Systems Academic Group (SP)
Organization
Identifiers
NPS Report Number
Sponsors
Funder
Format
Citation
Distribution Statement
Approved for public release. Distribution is unlimited.
Rights
This publication is a work of the U.S. Government as defined in Title 17, United States Code, Section 101. Copyright protection is not available for this work in the United States.