This is an early access version, the complete PDF, HTML, and XML versions will be available soon.
Open AccessArticle
Pixel-Level Decision Fusion for Land Cover Classification Using PolSAR Data and Local Pattern Differences
by
Spiros Papadopoulos
Spiros Papadopoulos
Spiros Papadopoulos received his Bachelor's degree in Physics from the University of Patras in 2021, [...]
Spiros Papadopoulos received his Bachelor's degree in Physics from the University of Patras in 2021, and he also received a Master's degree in Electronics and Information Processing in February 2023. He is currently a Ph.D candidate at Physics Department, University of Patras. His main research interests are in decision fusion methods of multi-band data for a more accurate land cover classification.
,
Vassilis Anastassopoulos
Vassilis Anastassopoulos
Vassilis Anastassopoulos is a Professor in the Electronics Laboratory, Physics Department, of Patras [...]
Vassilis Anastassopoulos is a Professor in the Electronics Laboratory, Physics Department, University of Patras (Bachelor in Physics, 1980; Ph.D. in Electronics, 1985). He worked for two years in Canada (University of Toronto, 1989-1990, and AUG Signals Ltd., 1994-1995). His research interests are within the scope of Digital Signal and Image Processing, Radar Signal Detection, Pattern Recognition, Remote Sensing, Handwritten Analysis and Biometrics, Information Fusion, Super Resolution, and Inverse Problems. He is teaching Electronics, Digital Signal and Image Processing, and Programming. He is the author of four books used for university teaching purposes. He has been the Associate Editor in the IEEE Transactions on Circuits and Systems II and in the Pattern Recognition Journal. He was appointed as an Advisor in the AFC ESA Committee (2005-2010). He was the Vice Rector for Research Planning in the University of Patras (2006-2010). He was also the President of Patras Science Park (2015-2021).
* and
Georgia Koukiou
Georgia Koukiou
Georgia Koukiou holds a B.Sc. in Physics, an M.Sc. in Electronics and Computers, and a Ph.D. in and [...]
Georgia Koukiou holds a B.Sc. in Physics, an M.Sc. in Electronics and Computers, and a Ph.D. in Digital Image Processing and Pattern Recognition from Physics Department, University of Patras, Greece. She is a member of the research team of the Digital Image and Signal Processing group in the Electronics Laboratory of the Physics Department, University of Patras, Greece. Her research interests include Face Identification using Thermal Infrared, Pattern Recognition, Biomedical Imaging, Remote Sensing, SAR Imaging, Ground-Penetrating Radar techniques, and Information Fusion, particularly Decision Fusion methods. She worked at VUB for the spring semester of 2013 in Biometrics and Thermal Imaging. She has been funded by two scholarships, one from the State Scholarships Institution for the detection of intoxicated persons, and the other from a State Project for Feature Fusion in the same field.
Electronics Laboratory, Physics Department, University of Patras, 26504 Patras, Greece
*
Author to whom correspondence should be addressed.
Electronics 2024, 13(19), 3846; https://doi.org/10.3390/electronics13193846 (registering DOI)
Submission received: 27 August 2024
/
Revised: 24 September 2024
/
Accepted: 26 September 2024
/
Published: 28 September 2024
Abstract
Combining various viewpoints to produce coherent and cohesive results requires decision fusion. These methodologies are essential for synthesizing data from multiple sensors in remote sensing classification in order to make conclusive decisions. Using fully polarimetric Synthetic Aperture Radar (PolSAR) imagery, our study combines the benefits of both approaches for detection by extracting Pauli’s and Krogager’s decomposition components. The Local Pattern Differences (LPD) method was employed on every decomposition component for pixel-level texture feature extraction. These extracted features were utilized to train three independent classifiers. Ultimately, these findings were handled as independent decisions for each land cover type and were fused together using a decision fusion rule to produce complete and enhanced classification results. As part of our approach, after a thorough examination, the most appropriate classifiers and decision rules were exploited, as well as the mathematical foundations required for effective decision fusion. Incorporating qualitative and quantitative information into the decision fusion process ensures robust and reliable classification results. The innovation of our approach lies in the dual use of decomposition methods and the application of a simple but effective decision fusion strategy.
Share and Cite
MDPI and ACS Style
Papadopoulos, S.; Anastassopoulos, V.; Koukiou, G.
Pixel-Level Decision Fusion for Land Cover Classification Using PolSAR Data and Local Pattern Differences. Electronics 2024, 13, 3846.
https://doi.org/10.3390/electronics13193846
AMA Style
Papadopoulos S, Anastassopoulos V, Koukiou G.
Pixel-Level Decision Fusion for Land Cover Classification Using PolSAR Data and Local Pattern Differences. Electronics. 2024; 13(19):3846.
https://doi.org/10.3390/electronics13193846
Chicago/Turabian Style
Papadopoulos, Spiros, Vassilis Anastassopoulos, and Georgia Koukiou.
2024. "Pixel-Level Decision Fusion for Land Cover Classification Using PolSAR Data and Local Pattern Differences" Electronics 13, no. 19: 3846.
https://doi.org/10.3390/electronics13193846
Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details
here.
Article Metrics
Article Access Statistics
For more information on the journal statistics, click
here.
Multiple requests from the same IP address are counted as one view.