Back to Search
Start Over
DATA AUGMENTATION FOR SYNTHETIC APERTURE RADAR USING ALPHA BLENDING AND DEEP LAYER TRAINING
- Publication Year :
- 2023
- Publisher :
- Monterey, CA; Naval Postgraduate School, 2023.
-
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. Outstanding Thesis Major, United States Air Force Approved for public release. Distribution is unlimited.
- Subjects :
- SAMPLE
convolutional neural network
wide area search
low-resolution
chip
area search
patch
AConvNet
synthetic dataset
FOV
object proposal
target proposal
MSTAR
background
target detection
tip-and-cue
feature detection
object detection
synthetic aperture radar (SAR)
artificial intelligence
ML
RADAR
machine learning
swath
alpha blending
AI
field of view
CNN
discovery
data augmentation
Subjects
Details
- Database :
- OpenAIRE
- Accession number :
- edsair.od......2778..32485e20bb532aac3029c2b9d9530157