Impact of PolSAR Pre-Processing and Balancing Methods on Complex-Valued Neural Networks Segmentation Tasks
In this article, we investigated the semantic segmentation of Polarimetric Synthetic Aperture Radar (PolSAR) using Complex-Valued Neural Network (CVNN). Although the coherency matrix is more widely used as the input of CVNN, the Pauli vector has recently been shown to be a valid alternative. We exha...
Main Authors: | Jose Agustin Barrachina, Chengfang Ren, Christele Morisseau, Gilles Vieillard, Jean-Philippe Ovarlez |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2023-01-01
|
Series: | IEEE Open Journal of Signal Processing |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/10048504/ |
Similar Items
-
MASA-SegNet: A Semantic Segmentation Network for PolSAR Images
by: Jun Sun, et al.
Published: (2023-07-01) -
AIR-PolSAR-Seg: A Large-Scale Data Set for Terrain Segmentation in Complex-Scene PolSAR Images
by: Zhirui Wang, et al.
Published: (2022-01-01) -
Your Input Matters—Comparing Real-Valued PolSAR Data Representations for CNN-Based Segmentation
by: Sylvia Hochstuhl, et al.
Published: (2023-12-01) -
Hierarchical Superpixel Segmentation for PolSAR Images Based on the Boruvka Algorithm
by: Jie Deng, et al.
Published: (2022-09-01) -
Multiobjective Evolutionary Superpixel Segmentation for PolSAR Image Classification
by: Boce Chu, et al.
Published: (2024-02-01)