A new classification method of SAR image based on OGMRF-RC model
A new classification method of SAR image based on OGMRF-RC model
- Author(s): Y. Li 1, 2, 3 ; Z. Guo 1, 2, 3 ; L. Wu 1, 3, 4 ; Z. Guo 1, 2, 3
- DOI: 10.1049/icp.2021.0665
For access to this article, please select a purchase option:
Buy conference paper PDF
Buy Knowledge Pack
IET members benefit from discounts to all IET publications and free access to E&T Magazine. If you are an IET member, log in to your account and the discounts will automatically be applied.
Thank you
Your recommendation has been sent to your librarian.
- Author(s): Y. Li 1, 2, 3 ; Z. Guo 1, 2, 3 ; L. Wu 1, 3, 4 ; Z. Guo 1, 2, 3
-
-
View affiliations
-
Affiliations:
1:
College of Computer and Information Engineering , Henan University , Kaifeng 475004 , PR China ;
2: Henan Key Laboratory of Big Data Analysis and Processing, Henan University , Kaifeng 475004 , PR China ;
3: Henan Engineering Research Center of Intelligent Technology and Application , Henan University , Kaifeng 475000 , PR China ;
4: College of Environment and Planning , Henan University , Kaifeng 475004 , PR China
Source:
IET International Radar Conference (IET IRC 2020),
2021
p.
1217 – 1221
-
Affiliations:
1:
College of Computer and Information Engineering , Henan University , Kaifeng 475004 , PR China ;
- Conference: IET International Radar Conference (IET IRC 2020)
- DOI: 10.1049/icp.2021.0665
- ISBN: 978-1-83953-540-6
- Location: Online Conference
- Conference date: 04-06 November 2020
- Format: PDF
Synthetic Aperture Radar (SAR) image classification is a key technique and research focus in the application of remote sensing. This paper proposes a new classification method of SAR image based on Object-based Gaussian-Markov Random Field model with Region Coefficients (OGMRF-RC), the new method use Fuzzy Probability (FP) represents the region's category probability, FP is obtained by regional posterior probability and edge information of neighborhood. Use FP to replace the unique class label of the region, which avoids the parameters estimation inaccurate of the feature field caused by the unique initial class label. And the parameter calculation method of feature field takes into account the feature information of all regions in the image. In this paper, we take the area around Baliwan in Kaifeng as study area, Sentinel-1 is used as the remote sensing data sources. FCM, K-means, classic MRF and OGMRF-RC are used as contrast methods, the experimental result demonstrates the accuracy of our method is better than these methods.
Inspec keywords: synthetic aperture radar; Gaussian processes; feature extraction; image classification; geophysical image processing; Markov processes; remote sensing; parameter estimation; probability; radar imaging
Subjects: Radar equipment, systems and applications; Markov processes; Image recognition; Geophysical techniques and equipment; Markov processes; Computer vision and image processing techniques; Radar theory; Instrumentation and techniques for geophysical, hydrospheric and lower atmosphere research; Probability theory, stochastic processes, and statistics