Nonlinear displacement analysis using cluster based PS extraction and Gaussian process regression
Konferenz: EUSAR 2021 - 13th European Conference on Synthetic Aperture Radar
29.03.2021 - 01.04.2021 in online
Tagungsband: EUSAR 2021
Seiten: 5Sprache: EnglischTyp: PDF
Tanaka, Taichi; Hoshuyama, Osamu (NEC Data Science Research Laboratories, Japan)
This paper proposes a nonlinear displacement analysis method using cluster based persistent scatterer (PS) extraction and Gaussian process regression. The cluster based PS method can extract PSs with low phase noise, which improves accuracy of spatial phase unwrapping required for dealing with nonlinear displacement. Gaussian process regression flexibly fits nonlinear displacement model to the unwrapped phase. The experimental results show that the proposed method obtains more accurate unwrapped phase and captures nonlinear displacements, even when 14 SAR images are available.