Analysis of spatially mismatched imagery for synthetic aperture radar ATR classification

Rupp, Chad T.; Halversen, S.D.; Montagnino, Lee J.; Hebert, Christina L.; Young, Matthew P.; Cassabaum, Mary L.; Ku, Neilson

doi:10.1117/12.778105

Search citation statements

Order By: Relevance

Paper Sections

Select...

Sar Data and Simulation Methods1

Citation Types

Supporting

Mentioning

Contrasting

Year Published

2023

2024

Publication Types

Select...

Other1

Article1

Relationship

Self Cite0

Independent2

Authors

Journals

Cited by 2 publications

(1 citation statement)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The T72 MBTs are different variants. The images are 128x128 pixels in size with a radar resolution of 0.3048 m (1 foot) 6 and pixel spacing 0.202 m in range and cross range 10 . Training data were collected at an elevation of 15° and test data at 17°.…”

Section: Sar Data and Simulation Methodsmentioning

confidence: 99%

Target Recognition in Sar Images With Low-Swap Processing Hardware

LANE,

HOLMES,

LAMONT-SMITH

2023

Synthetic Aperture Sonar and Synthetic Aperture Radar 2023

View full text Add to dashboard Cite

Section: Sar Data and Simulation Methodsmentioning

confidence: 99%

Target Recognition in Sar Images With Low-Swap Processing Hardware

LANE,

HOLMES,

LAMONT-SMITH

2023

Synthetic Aperture Sonar and Synthetic Aperture Radar 2023

View full text Add to dashboard Cite

Target recognition in diverse synthetic aperture radar image datasets with low size weight and power processing hardware

Lane,

Holmes,

Lamont‐Smith

2024

IET Radar Sonar & Navi

View full text Add to dashboard Cite

This paper studies the performance of target detection and classification algorithms applied to synthetic aperture radar (SAR) data. We describe a process to merge measured environmental SAR scene images with target image chips to produce a large dataset for training deep learning algorithms. Three algorithms, RetinaNet, EfficientDet, and YOLOv5, were trained using a powerful cloud server. Performance at inference time, in terms of speed and accuracy, was tested on both the cloud server and a low size weight and power (SWAP) single board computer. YOLOv5 was found to be the most accurate and fastest algorithm on the cloud server but the slowest on the low‐SWAP device. RetinaNet and EfficientDet produced operationally useful throughput on the low‐SWAP device for surveillance applications, with RetinaNet having the higher accuracy. Further qualitative analysis of algorithm performance on additional data with different characteristics highlighted the importance of gathering relevant training data and carrying out suitable pre‐processing steps.

show abstract

Analysis of spatially mismatched imagery for synthetic aperture radar ATR classification

Cited by 2 publications

References 0 publications

Target Recognition in Sar Images With Low-Swap Processing Hardware

Target Recognition in Sar Images With Low-Swap Processing Hardware

Target recognition in diverse synthetic aperture radar image datasets with low size weight and power processing hardware

Contact Info

Product

Resources

About