연구실적 · 학술회의 발표
A new similarity evaluation method that reflects the characteristics of SAR images based on statistical quality measurement
DOI초록
Unlike imaging using electro-optical payloads (EO), images acquired through satellites equipped with synthetic aperture radar (SAR) are generated based on electromagnetic waves and ground surface characteristics. Due to these characteristics, SAR images have the advantage of being able to be used in a variety of environments and can be operated in all-weather environments, depending on the use of electromagnetic wave technology. However, the ground surface is time dependent and the scattering results appear different even if images were taken of the same area due to geometric distortion, complex scattering, or radiation from structures. Therefore, it is difficult to apply the similarity evaluation method applied to conventional optical images due to the unique characteristic of SAR image that the similarity between images may appear low even if they were taken at a similar time. In this paper, we propose a new similarity evaluation method based on statistical quality measurement that reflects the characteristics of the real SAR image and describe the experimental results with real SAR images using fake SAR images generated by synthesis or data augmentation.
사이트 원문 표기
Taeseung Lee, Changhan Park, Junyoung Ko, Moonsung Huh, Byoungjun Kim, Heewoo Lee, Byungtae Oh, Wookyung Lee, “A new similarity evaluation method that reflects the characteristics of SAR images based on statistical quality measurement”, Proc. SPIE 13463, Automatic Target Recognition XXXV (SPIE Defense + Commercial Sensing 2025, Orlando, 13-17 April 2025), vol. 13463, 2025
BibTeX
@inproceedings{Lee_2025,
title={A new similarity evaluation method that reflects the characteristics of SAR images based on statistical quality measurement},
url={http://dx.doi.org/10.1117/12.3053419},
DOI={10.1117/12.3053419},
booktitle={Automatic Target Recognition XXXV},
publisher={SPIE},
author={Lee, Taeseung and Park, Changhan and Ko, Junyoung and Huh, Moonsung and Kim, Byoungjun and Lee, Heewoo and Oh, Byungtae and Lee, Wookyung},
editor={Chen, Kenny and Overman, Timothy L. and Hammoud, Riad I.},
year={2025},
month=May,
pages={13}
}