Next Article in Journal
Application and Comparison of Satellite-Derived Sea Surface Temperature Gradients to Identify Seasonal and Interannual Variability off the California Coast: Preliminary Results and Future Perspectives
Previous Article in Journal
Rapid 3D Camera Calibration for Large-Scale Structural Monitoring
Previous Article in Special Issue
A False-Positive-Centric Framework for Object Detection Disambiguation
 
 
Font Type:
Arial Georgia Verdana
Font Size:
Aa Aa Aa
Line Spacing:
Column Width:
Background:
This is an early access version, the complete PDF, HTML, and XML versions will be available soon.
Article

PolSAR-SFCGN: An End-to-End PolSAR Superpixel Fully Convolutional Generation Network

1
Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education, School of Artificial Intelligence, Xidian University, Xi’an 710071, China
2
School of Engineering, Xidian University, Xi’an 710071, China
3
54th Research Institute of China Electronics Technology Group Corporation, Shijiazhuang 050081, China
*
Author to whom correspondence should be addressed.
Remote Sens. 2025, 17(15), 2723; https://doi.org/10.3390/rs17152723
Submission received: 19 May 2025 / Revised: 1 August 2025 / Accepted: 4 August 2025 / Published: 6 August 2025

Abstract

Polarimetric Synthetic Aperture Radar (PolSAR) image classification is one of the most important applications in remote sensing. The impressive superpixel generation approaches can improve the efficiency of the subsequent classification task and restrain the influence of the speckle noise to an extent. Most of the classical PolSAR superpixel generation approaches use the features extracted manually and even only consider the pseudocolor images. They do not make full use of polarimetric information and do not necessarily lead to good enough superpixels. The deep learning methods can extract effective deep features but they are difficult to combine with superpixel generation to achieve true end-to-end training. Addressing the above issues, this study proposes an end-to-end fully convolutional superpixel generation network for PolSAR images. It integrates the extraction of polarization information features and the generation of PolSAR superpixels into one step. PolSAR superpixels can be generated based on deep polarization feature extraction and need no traditional clustering process. Both the performance and efficiency of generations of PolSAR superpixels can be enhanced effectively. The experimental results on various PolSAR datasets show that the proposed method can achieve impressive superpixel segmentation by fitting the real boundaries of different types of ground objects effectively and efficiently. It can achieve excellent classification performance by connecting a very simple classification network, which is helpful to improve the efficiency of the subsequent PolSAR image classification tasks.
Keywords: superpixel generation; end-to-end; fully convolutional network; polarimetric information; Polarimetric Synthetic Aperture Radar image classification superpixel generation; end-to-end; fully convolutional network; polarimetric information; Polarimetric Synthetic Aperture Radar image classification

Share and Cite

MDPI and ACS Style

Zhang, M.; Shi, J.; Liu, L.; Zhang, W.; Feng, J.; Zhu, J.; Chu, B. PolSAR-SFCGN: An End-to-End PolSAR Superpixel Fully Convolutional Generation Network. Remote Sens. 2025, 17, 2723. https://doi.org/10.3390/rs17152723

AMA Style

Zhang M, Shi J, Liu L, Zhang W, Feng J, Zhu J, Chu B. PolSAR-SFCGN: An End-to-End PolSAR Superpixel Fully Convolutional Generation Network. Remote Sensing. 2025; 17(15):2723. https://doi.org/10.3390/rs17152723

Chicago/Turabian Style

Zhang, Mengxuan, Jingyuan Shi, Long Liu, Wenbo Zhang, Jie Feng, Jin Zhu, and Boce Chu. 2025. "PolSAR-SFCGN: An End-to-End PolSAR Superpixel Fully Convolutional Generation Network" Remote Sensing 17, no. 15: 2723. https://doi.org/10.3390/rs17152723

APA Style

Zhang, M., Shi, J., Liu, L., Zhang, W., Feng, J., Zhu, J., & Chu, B. (2025). PolSAR-SFCGN: An End-to-End PolSAR Superpixel Fully Convolutional Generation Network. Remote Sensing, 17(15), 2723. https://doi.org/10.3390/rs17152723

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Metrics

Article metric data becomes available approximately 24 hours after publication online.
Back to TopTop