Abstract
Traditional Selection of Homogeneous Pixels (SHP) methods insufficiently utilize polarization information and rely on extensive statistical computations from large datasets. When applied to mountainous or densely vegetated regions with low coherence, these methods are susceptible to noise interference, which reduces the interpretation reliability. In this study, we propose ViTPolSHP———the Vision Transformer(ViT)-based Polarimetric Synthetic Aperture Radar (PolSAR) Selection of Homogeneous Pixels algorithm for selecting homogeneous pixels in multi-temporal PolSAR imagery. The ViTPolSHP algorithm leverages the temporal average Yamaguchi four-component decomposition features for classification and integrates the terrain characteristics and geometric distortions to derive homogeneous pixel sets even with limited datasets, presenting a promising solution for SAR/InSAR data processing in complex mountainous terrains.
Funding Information
  • National Natural Science Foundation of China (42030112)
  • Major Scientific and Technological Projects of Hunan Geological Institute (HNGSTP202303)
  • science and technology innovation Program of Hunan Province (2022RC3042)
  • science and technology innovation Program of Hunan Province (2023SK2012)

This publication has 18 references indexed in Scilit: