PolSAR Image Classification by Introducing POA and HA Variances

A polarimetric synthetic aperture radar (PolSAR) has great potential in ground target classification. However, current methods experience difficulties in separating forests and buildings, especially oriented buildings. To address this issue, inspired by the three-component decomposition method, mult...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Remote sensing (Basel, Switzerland) Switzerland), 2023-09, Vol.15 (18), p.4464
Hauptverfasser: Lan, Zeying, Liu, Yang, He, Jianhua, Hu, Xin
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:A polarimetric synthetic aperture radar (PolSAR) has great potential in ground target classification. However, current methods experience difficulties in separating forests and buildings, especially oriented buildings. To address this issue, inspired by the three-component decomposition method, multiple new scattering models were proposed to describe the difference between forest scattering and building scattering. However, this problem cannot effectively be solved with scattering power alone since HV polarization records significant scattering powers from building areas that are similar to vegetation. Therefore, in this study, two new parameters, the polarization orientation angle (POA) variance and helix angle (HA) variance, were defined to describe the distributions of buildings and forests. By combining scattering power with POA and HA variances, the random forest algorithm was used to conduct the land cover classification, focusing on distinguishing between forests and oriented buildings. Finally, the C- and L-band polarimetric SAR data acquired by the GF-3, ALOS1 PALSAR, and SAOCOM systems were selected to test the proposed method. The results indicate that it is feasible to improve PolSAR classification accuracy by introducing polarimetric parameters. Quantitatively, the classification accuracies increased by 23.78%, 10.80%, and 12.97% for the ALOS1 PALSAR, GF-3, and SAOCOM data, respectively.
ISSN:2072-4292
2072-4292
DOI:10.3390/rs15184464