Land Cover Classification of SAR Based on 1DCNN-MRF Model Using Improved Dual-Polarization Radar Vegetation Index
نویسندگان
چکیده
Accurate land cover classification (LCC) is essential for studying global change. Synthetic aperture radar (SAR) has been used LCC due to its advantage of weather independence. In particular, the dual-polarization (dual-pol) SAR data have a wider coverage and are easier obtain, which provides an unprecedented opportunity LCC. However, dual-pol weak discrimination ability limited polarization information. Moreover, complex imaging mechanism leads speckle noise images, also decreases accuracy To address above issues, improved vegetation index based on multiple components (DpRVIm) new method proposed data. Firstly, in DpRVIm, scattering information terrain factors were considered improve separability ground objects Then, Jeffries-Matusita (J-M) distance one-dimensional convolutional neural network (1DCNN) algorithm analyze effect difference indexes Finally, order reduce influence noise, two-stage method, 1DCNN-MRF, 1DCNN Markov random field (MRF) was designed considering spatial objects. this study, HH-HV model Gaofen-3 satellite Dongting Lake area used, results showed that: (1) Through combination backscatter coefficient decomposition technique, can be compared with single coefficient. (2) The DpRVIm more conducive improving than classic (DpRVI) (RVI), especially farmland forest. (3) Compared machine learning methods K-nearest neighbor (KNN), forest (RF), 1DCNN, 1DCNN-MRF achieved highest accuracy, overall (OA) score 81.76% Kappa (Kappa) 0.74. This study indicated application potential technique DEM enhancing different types Furthermore, it demonstrated that deep networks MRF suitable suppress noise.
منابع مشابه
Land Cover Classification Using E-sar Polarimetric Data
Different decomposition approaches have been proposed in order to analyse and interpret SAR polarimetric images. These are based either on the complex voltage reflection matrix, like Pauli, or on power reflection matrix, like the covariance or coherency matrix. They produce polarimetric parameters which are appropriate to retrieve information on the scattering process of the target. If the targ...
متن کاملAutomated Ice-Water Classification Using Dual Polarization SAR Satellite Imagery
Mapping ice and open water in ocean bodies is important for numerous purposes including environmental analysis and ship navigation. The Canadian Ice Service (CIS) has stipulated a need for an automated ice-water discrimination algorithm using dual polarization images produced by RADARSAT2. Automated methods can provide mappings in larger volumes, with more consistency, and in finer resolutions ...
متن کاملStatistical Modeling for Improved Land Cover Classification
Novel statistical modeling and training techniques are proposed for improving classification accuracy of land cover data acquired by LandSat Thermatic Mapper (TM). The proposed modeling techniques consist of joint modeling of spectral feature distributions among neighboring pixels and partial modeling of spectral correlations across TM sensor bands with a set of semi-tied covariance matrices in...
متن کاملLand Cover Identification Using Polarimetric Sar Images
Synthetic Aperture Radar (SAR) has been proven to be a powerful earth observation tool. Due to its sensitivity to vegetation, its orientations and various land-covers, SAR polarimetry has the potential to become a principle mean for crop and land-cover classification. A variety of polarimetric classification algorithms have been proposed in the literature for segmentation and/or classification ...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Remote Sensing
سال: 2023
ISSN: ['2315-4632', '2315-4675']
DOI: https://doi.org/10.3390/rs15133221