High resolution SAR image classification
نویسندگان
چکیده
In this report we propose a novel classification algorithm for high and very high resolution synthetic aperture radar (SAR) amplitude images that combines the Markov random field approach to Bayesian image classification and a finite mixture technique for probability density function estimation. The finite mixture modeling is done by dictionarybased stochastic expectation maximization amplitude histogram estimation approach. The developed semiautomatic algorithm is extended to an important case of multi-polarized SAR by modeling the joint distributions of channels via copulas. The accuracy of the proposed algorithm is validated for the application of wet soil classification on several high resolution SAR images acquired by TerraSAR-X and COSMO-SkyMed. Key-words: SAR image classification, dictionary, amplitude probability density, stochastic expectation maximization, Markov random field, copula ∗ EPI Ariana, CR INRIA Sophia Antipolis Méditeranée, 2004, Route des Lucioles, B.P.93, FR-06902, Sophia Antipolis Cedex (France); Faculty of Computational Mathematics and Cybernetics, Lomonosov Moscow State University, 119991 Leninskie Gory, Moscow (Russia), e-mail: [email protected]. † EPI Ariana, CR INRIA Sophia Antipolis Méditeranée, 2004, Route des Lucioles, B.P.93, FR-06902, Sophia Antipolis Cedex (France), e-mail: [email protected]. in ria -0 04 33 03 6, v er si on 2 13 D ec 2 00 9 Classification des images RSO haute résolution Résumé : Dans ce rapport, nous proposons une nouvelle approche pour la classification des images de type Radar à Synthèse d’Ouverture (RSO) haute résolution. Cette approche combine la méthode des champs Markoviens pour la classification bayésienne et un modèle de mélange fini pour l’estimation des densités de probabilité. Ce modèle de mélange fini est realisé grace à une approche fondée sur une espérance-maximisation stochastique, à partir d’un dictionnaire, pour l’estimation des densités de probabilité d’amplitude. Cette approche semi-automatique est étendue au cas important des images RSO avec plusieurs polarisations, en utilisant des copulas pour modéliser les distributions jointes. Des résultats expérimentaux, sur plusieurs images RSO réelles (Dual-Pol TerraSAR-X et SingePol COSMO-SkyMed), pour la classification de zones humides, sont présentés pour montrer l’efficacité de l’algorithme proposé. Mots-clés : classification d’image RSO, dictionnaire, densité de probabilité d’amplitude, espérance-maximisation stochastique, champ Markovien, copula in ria -0 04 33 03 6, v er si on 2 13 D ec 2 00 9 High resolution SAR image classification 3
منابع مشابه
Palarimetric Synthetic Aperture Radar Image Classification using Bag of Visual Words Algorithm
Land cover is defined as the physical material of the surface of the earth, including different vegetation covers, bare soil, water surface, various urban areas, etc. Land cover and its changes are very important and influential on the Earth and life of living organisms, especially human beings. Land cover change monitoring is important for protecting the ecosystem, forests, farmland, open spac...
متن کاملObject-Oriented Method for Automatic Extraction of Road from High Resolution Satellite Images
As the information carried in a high spatial resolution image is not represented by single pixels but by meaningful image objects, which include the association of multiple pixels and their mutual relations, the object based method has become one of the most commonly used strategies for the processing of high resolution imagery. This processing comprises two fundamental and critical steps towar...
متن کاملPolarimetric SAR Image Classification with High Frequency Component Derived from Wavelet Multi Resolution Analysis: MRA
A method for polarimetric Synthetic Aperture Radar: SAR image classification with high frequency component derived from wavelet Multi-Resolution Analysis: MRA is proposed. Although it is well known that polarization signature derived from fully polarized SAR data is useful for SAR image classifications, it is still unknown how to utilize the polarization signature in the image classification. H...
متن کاملClassification of High Resolution Optical and Sar Fusion Image Using Fuzzy Knowledge and Object-oriented Paradigm
The fusion image of IKONOS optical data and COSMO-SkyMed SAR image is used as the classifier inputs for land cover classification under an object-oriented paradigm. Firstly, Frost filter is selected to reduce speckle noises of SAR image. Three popular methods, including IHS, PCA and wavelet transform, are applied to fuse high resolution optical and SAR images. Comparing with other fusion method...
متن کاملLearning from label proportions for SAR image classification
Synthetic aperture radar (SAR) image classification plays a key role in SAR interpretation. Due to the cost and difficulty of truth labeling for SAR images, the newly labeled samples available for image classification are very limited. This paper focuses on defining a new sample labeling method to solve the problem of truth acquisition for training data in SAR image classification. An efficient...
متن کاملHigh resolution SAR-image classification by Markov random fields and finite mixtures
In this paper we develop a novel classification approach for high and very high resolution polarimetric synthetic aperture radar (SAR) amplitude images. This approach combines the Markov random field model to Bayesian image classification and a finite mixture technique for probability density function estimation. The finite mixture modeling is done via a recently proposed dictionary-based stoch...
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 2009