Classification of Polarimetric Sar Images Based on Scattering Mechanisms
نویسندگان
چکیده
Polarimetric classification is one of the most significant applications of polarimetric radar in remote sensing. During the last decade, several research tasks revealed the contribution of polarimetric data in classification of soil types and landcover. They contributed thus to a better comprehension of the scattering mechanisms. We propose in this paper a strategy analysis for forest types discrimination and their cartography on the ground using fully polarimetric data based on scattering matrix decompositions. To determine the scattering mechanism associated to each pixel with the target, we developed a supervised classification procedure where the training set is established from the entropy/Alpha space. The polarimetric coherence matrix was used to determine soil scattering parameters. To this end, we described two scattering types: deterministic scattering and random scattering. Classification of the image gives good discrimination of forests types and the results are checked using polarimetric signatures. The test area used is the Oberpfaffenhofen in Munich. The SAR images are acquired in the P band. RESUME: La classification polarimétrique est l’une des applications les plus importante de la polarimétrie radar en télédétection. Durant la dernière décennie, plusieurs travaux de recherche ont montré la contribution des données polarimétriques en classification des types de sols et les types de couverts de sol. Ainsi, ils ont contribué à une meilleure compréhension des mécanismes de diffusion. Nous proposons dans cette article une stratégie d’analyse pour la discrimination des types de forets et leur cartographie sur le sol, en utilisant des données radar complètement polarimétrique basé sur la décomposition de la matrice de diffusion. Pour déterminer le mécanisme de diffusion associé à chaque pixel avec la cible, nous avons développé une classification supervisée, ou la base d’entraînement est établit à partir de l’espace entropie/Alpha. La matrice polarimétrique de cohérence a été utilisée pour déterminer les paramètres de diffusion du sol. Dans ce but, nous décrivons deux types de diffusion : Diffusion déterministe et diffusion aléatoire. La classification de l’image donne une bonne discrimination des types de forêts et les résultas sont vérifiées en utilisant les signatures polarimétriques. Le site d’étude est la zone de Oberpfafenhoffen à Munich. Les images RSO sont acquises dans la bande P.
منابع مشابه
Microwave Imaging Using SAR
Polarimetric Synthetic Aperture Radar (Pol.-SAR) allows us to implement the recognition and classification of radar targets. This article investigates the arrangement of scatterers by SAR data and proposes a new Look-up Table of Region (LTR). This look-up table is based on the combination of (entropy H/Anisotropy A) and (Anisotropy A/scattering mechanism α), which has not been reported up now. ...
متن کاملChange Detection in Urban Area Using Decision Level Fusion of Change Maps Extracted from Optic and SAR Images
The last few decades witnessed high urban growth rates in many countries. Urban growth can be mapped and measured by using remote sensing data and techniques along with several statistical measures. The purpose of this research is to detect the urban change that is used for urban planning. Change detection using remote sensing images can be classified into three methods: algebra-based, transfor...
متن کاملRelation between degree of polarization and Pauli color coded image to characterize scattering mechanisms
Polarimetric image classification is sensitive to object orientation and scattering properties. This paper is a preliminary step to bridge the gap between visible wavelength polarimetric imaging and polarimetric SAR (POLSAR) imaging scattering mechanisms. In visible wavelength polarimetric imaging, the degree of linear polarization (DOLP) is widely used to represent the polarized component of t...
متن کاملA Combined Use of Decomposition and Texture for Terrain Classification of Fully Polarimetric Sar Images
This paper presents two-stage unsupervised terrain classification of fully polarimetric SAR data using Freeman and Durden decomposition based on three simple scattering mechanisms: surface, volume and double bounce (first step), and textural features (uncorrelated uniformity, contrast, inverse moment and entropy) obtained from grey level co-occurrence matrices (GLCM) (second step). Textural fea...
متن کاملClassification of Polarimetric SAR Image Based on Support Vector Machine Using Multiple-Component Scattering Model and Texture Features
The classification of polarimetric SAR image based on Multiple-Component Scattering Model (MCSM) and Support Vector Machine (SVM) is presented in this paper. MCSM is a potential decomposition method for a general condition. SVM is a popular tool for machine learning tasks involving classification, recognition, or detection. The scattering powers of single-bounce, doublebounce, volume, helix, an...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2007