Coherence matrix power model for scattering variation representation in multi-temporal PolSAR crop classification

The multi-temporal polarimetric SAR (PolSAR) data contains the scattering change information during the growth of crops. However, the current classification methods usually directly use the addition of features extracted at single-temporal or use the temporal and spatial variations of certain featur...

ver descrição completa

Detalhes bibliográficos
Autores: Yin, Qiang, Gao, Li, Zhou, Yongsheng, Li, Yang, Zhang, Fan, López Martínez, Carlos|||0000-0002-1366-9446, Hong, Wen
Tipo de documento: artigo
Data de publicação:2024
País:España
Recursos:Universitat Politècnica de Catalunya (UPC)
Repositório:UPCommons. Portal del coneixement obert de la UPC
Idioma:inglês
OAI Identifier:oai:upcommons.upc.edu:2117/407754
Acesso em linha:https://hdl.handle.net/2117/407754
https://dx.doi.org/10.1109/JSTARS.2024.3395689
Access Level:Acceso aberto
Palavra-chave:Synthetic aperture radar
Remote sensing
Multi-temporal PolSAR
Crop classification
Data representation model
Scattering variation
Vision transformer
Radar d'obertura sintètica
Teledetecció
Àrees temàtiques de la UPC::Enginyeria de la telecomunicació::Radiocomunicació i exploració electromagnètica::Teledetecció
Descrição
Resumo:The multi-temporal polarimetric SAR (PolSAR) data contains the scattering change information during the growth of crops. However, the current classification methods usually directly use the addition of features extracted at single-temporal or use the temporal and spatial variations of certain features, not really exploring the complete scattering variation information. The specific data representation models for multi-temporal PolSAR data should combine time with polarimetry to characterize the scattering variations. However, the characterization and utilization of such kind of models are inadequate. In this article, we construct data representation model based on the power form of coherence matrix to comprehensively represent all kinds of scattering mechanism variation, which is full-rank positive semi-definite Hermitian matrix. We extract new time-variant scattering features and design vision transformer classifier accordingly for crop classification. Experiment results on RADARSAT-2 datasets show that the proposed power representation model outperforms other models.