Results 51 to 60 of about 13,122,784 (192)

PolSAR Image Classification Using a Superpixel-Based Composite Kernel and Elastic Net

, 2021
The presence of speckles and the absence of discriminative features make it difficult for the pixel-level polarimetric synthetic aperture radar (PolSAR) image classification to achieve more accurate and coherent interpretation results, especially in the ...
Yan Wu, Ming Li, Yice Cao, Peng Zhang, Wenkai Liang   +4 more
core   +1 more source

Deep support vector machine for PolSAR image classification

, 2021
The main problem posed by Polarimetric Synthetic Aperture Radar (PolSAR) image classification in remote sensing is the ability to develop classifiers that can substantially discern the different classes inherent in natural and man-made targets.
Olayinka, Dupe Nihinlola, Ndehedehe, Christopher, Okwuashi, Onuwa, Attai, Hosanna, Eyoh, Aniekan, Christopher E. Ndehedehe, Dupe Nihinlola Olayinka, Onuwa Okwuashi, Aniekan Eyoh, Hosanna Attai   +9 more
core   +1 more source

Dual-Branch Fusion of Convolutional Neural Network and Graph Convolutional Network for PolSAR Image Classification

, 2022
Polarimetric synthetic aperture radar (PolSAR) images contain useful information, which can lead to extensive land cover interpretation and a variety of output products.
Masoud Mahdianpari, Brian Brisco, Bahram Salehi, Fariba Mohammadimanesh, Ali Radman   +4 more
core   +1 more source

An Innovative Supervised Classification Algorithm for PolSAR Image Based on Mixture Model and MRF

, 2022
The Wishart mixture model is an effective tool for characterizing the statistical distribution of polarimetric synthetic aperture radar (PolSAR) data. However, due to the difficulty in determining the equivalent number of looks, the Wishart mixture model
Yao Gao, Chunle Wang, Wentao Hou, Xiuqing Liu, Yunkai Deng, Mingliang Liu, Chuanzhao Han   +6 more
core   +1 more source

Observation and Coordination Needs for Current, Near‐Future, and Next Generation Earth‐Observing SAR Systems

Earth and Space Science, Volume 13, Issue 5, May 2026.
Abstract This paper summarizes an evaluation by experts of how coordination of Earth‐observing Synthetic Aperture Radar (SAR) missions among the world's space agencies could advance toward game‐changing scientific discoveries and fully realizing SAR's practical capability to address many issues facing society.
Cathleen E. Jones, Ake Rosenqvist, Björn Rommen, Magdalena Fitrzyk, Eric Rignot, Bernd Scheuchl, Yujie Zheng, Andrew Hooper, Mark Simons, Tomokazu Kobayashi, Paul Siqueira, Maurizio Santoro, Takeo Tadono, Laura Hess, Heather McNairn, Laura Frulla, Malin Johansson, Wolfgang Dierking, Line Rouyet, Annett Bartsch, Paco Lopez Dekker, Johnny A. Johannessen   +21 more
wiley   +1 more source

Interlinked Dynamics of Rice Cultivation Intensity and Ground Subsidence: Spatio‐Temporal Insights Into Water Resource Implications From Multi‐Year Spaceborne SAR Analysis

Water Resources Research, Volume 62, Issue 4, April 2026.
Abstract Sustainable rice cultivation is vital to meet global food demands, particularly in regions relying on groundwater for irrigation. Over‐pumping, however, can cause significant ground subsidence, threatening both infrastructure and agricultural sustainability.
Ya‐Lun S. Tsai, Xun‐Yan Liu
wiley   +1 more source

Low frequency and radar’s physical based features for improvement of convolutional neural networks for PolSAR image classification

Egyptian Journal of Remote Sensing and Space Sciences, 2022
Although various deep neural networks such as convolutional neural networks (CNNs) have been suggested for classification of polarimetric synthetic aperture radar (PolSAR) images, but, they have several deficiencies.
Maryam Imani
doaj   +1 more source

A Box Gradient‐Based Anisotropic Diffusion Framework for Polarimetric SAR Despeckling

Electronics Letters, Volume 62, Issue 1, January/December 2026.
This paper proposes a novel anisotropic diffusion framework for PolSAR despeckling, driven by a newly defined complex‐domain Box gradient. The method adaptively suppresses speckle while preserving structural and point‐target details, and experiments on real AIRSAR data confirm superior performance over existing filters.
Songli Han, Dawei Ren, Jian Yang
wiley   +1 more source

Exploring Polarimetric Properties Preservation for PolSAR Image Reconstruction With Complex‐Valued Convolutional Neural Networks

IET Radar, Sonar &Navigation, Volume 20, Issue 1, January/December 2026.
Polarimetric SAR data's inherent complex‐valued nature demands algorithms that work directly with complex representations, yet most deep‐learning approaches sidestep this by converting to the real domain. We implement and evaluate complex‐valued convolutional autoencoders that compress and accurately reconstruct full‐polarimetric SAR signals—preserving
Quentin Gabot, Joana Frontera‐Pons, Jérémy Fix, Chengfang Ren, Jean‐Philippe Ovarlez   +4 more
wiley   +1 more source

Polarimetric SAR Image Classification Based on Ensemble Dual-Branch CNN and Superpixel Algorithm

IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2022
Recently, convolutional neural networks (CNNs) have been successfully utilized in polarimetric synthetic aperture radar (PolSAR) image classification and obtained promising results. However, most CNN-based classification methods require a large number of
Wenqiang Hua, Cong Zhang, Wen Xie, Xiaomin Jin   +3 more
doaj   +1 more source