Land Cover Feature recognition by fusion of PolSAR, PolInSAR and optical data

Size: px
Start display at page:

Download "Land Cover Feature recognition by fusion of PolSAR, PolInSAR and optical data"

Transcription

1 Land Cover Feature recognition by fusion of PolSAR, PolInSAR and optical data Shimoni, M., Borghys, D., Heremans, R., Milisavljević, N., Pernel, C. Derauw, D., Orban, A. PolInSAR Conference, ESRIN, January 2007

2 RESEARCH GOALS The main research goal is to fuse different frequency E-SAR PolSAR data as well as PolInSAR with Daedalus optical data for land cover classification and land cover feature recognition. This research also assigns the following target assessments: Do fused features from different SAR frequencies are complementary and adequate for land cover classification; Do PolInSAR features are complementary to the PolSAR information and essential for producing accurate classification of different land cover types as man-made object, water bodies, forest, crops and bare soils; Do optical data are complementary information for the SAR data and are necessary for the production of accurate land-cover classification. DATA SET Test site : Glinska Poljana, Croatia. Date : 6 to 10 August 2001; SAR: E-SAR L-band, P-band full polarimetric and dual-pass interferometry data set, resolution: 2 m (L) and 4 m (P); Optical: Daedalus 10 bands µm, resolution: 1 m; Excessive ground truth campaign

3 DERIVED FEATURE SETS PolSAR PolInSAR Optical PolSAR coherences Pauli decomposition Krogager decomposition Optimal coherences Mean magnitude Eigenvalue λ 1 Daedalus bands Freeman decomposition Huynen decomposition Barnes decomposition Eigenvalue λ 2 Stdv of the magnitude γ Stdv of the phase φ PCA234 H/A/α decomposition Asymetry Holm decomposition Neumann decomposition Lee Classifier A 1 Lee Classifier A 2 Directional filter 25 L-band PolSAR 25 P-band PolSAR 13 L-band PolinSAR 13 P-band PolinSAR 26 Optical

4 Feature based fusion 19 classifications High decision level fusion

5 FUSION METHODS Feature level fusion using Logistic Regression (LR): Finds an optimal combination of channels for detecting a given class, based on the learning set: N p x, y r ( TgtClass C) exp β0 + i = 1+ exp β0 + = 1 N Ci ( x, y) βi Ci ( x, y) βi 1 Implicit channel selection by using step-wise optimisation method for finding β i s. FUZZY based decision fusion: The fuzzy set theory allows an object to have partial membership in more than one set: A = {( x, µ A( x)) x X} µ A (x) is the grade of membership of x in A which maps X to the membership space M. For each class, we combine the classification results using maximum rule. i=

6 RESULTS

7 CONCLUSIONS L-band HH SLC scene Pauli decomposition LR classification results Fuzzy classification results For both fusion methods the overall accuracy for each of the fused sets is better than the accuracy for the separate sets of features; Fused features from different SAR frequencies are complementary and adequate for land cover classification; PolInSAR features are complementary to the PolSAR information and essential for producing accurate classification of different land cover types as man-made object, water bodies, forest, crops and bare soils; The optical data is complementary information for the SAR data but not necessary for the production of accurate land-cover classification; The overall fusion performance of the fuzzy-based approach is slightly better than the feature fusion by logistic regression for most of the combinations of feature sets.

Spectral Clustering of Polarimetric SAR Data With Wishart-Derived Distance Measures

Spectral Clustering of Polarimetric SAR Data With Wishart-Derived Distance Measures Spectral Clustering of Polarimetric SAR Data With Wishart-Derived Distance Measures STIAN NORMANN ANFINSEN ROBERT JENSSEN TORBJØRN ELTOFT COMPUTATIONAL EARTH OBSERVATION AND MACHINE LEARNING LABORATORY

More information

Polarimetry-based land cover classification with Sentinel-1 data

Polarimetry-based land cover classification with Sentinel-1 data Polarimetry-based land cover classification with Sentinel-1 data Banqué, Xavier (1); Lopez-Sanchez, Juan M (2); Monells, Daniel (1); Ballester, David (2); Duro, Javier (1); Koudogbo, Fifame (1) 1. Altamira-Information

More information

Evaluation and Bias Removal of Multi-Look Effect on Entropy/Alpha /Anisotropy (H/

Evaluation and Bias Removal of Multi-Look Effect on Entropy/Alpha /Anisotropy (H/ POLINSAR 2009 WORKSHOP 26-29 January 2009 ESA-ESRIN, Frascati (ROME), Italy Evaluation and Bias Removal of Multi-Look Effect on Entropy/Alpha /Anisotropy (H/ (H/α/A) Jong-Sen Lee*, Thomas Ainsworth Naval

More information

Intégration de connaissance experte

Intégration de connaissance experte Intégration de connaissance experte dans des systèmes de fusion d informationsd Florentin BUJOR, Gabriel VASILE, Lionel VALET Emmanuel TROUVÉ, Gilles MAURIS et Philippe BOLON emmanuel.trouve@univ-savoie.fr

More information

POLARIMETRY-BASED LAND COVER CLASSIFICATION WITH SENTINEL-1 DATA

POLARIMETRY-BASED LAND COVER CLASSIFICATION WITH SENTINEL-1 DATA POLARIMETRY-BASED LAND COVER CLASSIFICATION WITH SENTINEL-1 DATA Xavier Banqué (1), Juan M Lopez-Sanchez (2), Daniel Monells (1), David Ballester (2), Javier Duro (1), Fifame Koudogbo (1) (1) Altamira

More information

Making a case for full-polarimetric radar remote sensing

Making a case for full-polarimetric radar remote sensing Making a case for full-polarimetric radar remote sensing Jeremy Nicoll Alaska Satellite Facility, University of Alaska Fairbanks 1 Polarization States of a Coherent Plane Wave electric field vector vertically

More information

ADVANCED CONCEPTS POLSARPRO V3.0 LECTURE NOTES. Eric POTTIER (1), Jong-Sen LEE (2), Laurent FERRO-FAMIL (1)

ADVANCED CONCEPTS POLSARPRO V3.0 LECTURE NOTES. Eric POTTIER (1), Jong-Sen LEE (2), Laurent FERRO-FAMIL (1) ADVANCED CONCEPTS Eric POTTIER (), Jong-Sen LEE (), Laurent FERRO-FAMIL () () I.E.T.R UMR CNRS 664 University of Rennes Image and Remote Sensing Department, SAPHIR Team Campus de Beaulieu, Bat D, 63 Av

More information

DUAL FREQUENCY POLARIMETRIC SAR DATA CLASSIFICATION AND ANALYSIS

DUAL FREQUENCY POLARIMETRIC SAR DATA CLASSIFICATION AND ANALYSIS Progress In Electromagnetics Research, PIER 31, 247 272, 2001 DUAL FREQUENCY POLARIMETRIC SAR DATA CLASSIFICATION AND ANALYSIS L. Ferro-Famil Ecole Polytechnique de l Université de Nantes IRESTE, Laboratoire

More information

EVALUATION OF CLASSIFICATION METHODS WITH POLARIMETRIC ALOS/PALSAR DATA

EVALUATION OF CLASSIFICATION METHODS WITH POLARIMETRIC ALOS/PALSAR DATA EVALUATION OF CLASSIFICATION METHODS WITH POLARIMETRIC ALOS/PALSAR DATA Anne LÖNNQVIST a, Yrjö RAUSTE a, Heikki AHOLA a, Matthieu MOLINIER a, and Tuomas HÄME a a VTT Technical Research Centre of Finland,

More information

The 3rd International Workshop on Science and Applications of SAR Polarimetry and Polarimetric Interferometry

The 3rd International Workshop on Science and Applications of SAR Polarimetry and Polarimetric Interferometry SP-644 March 2007 Proceedings of PolInSAR 2007 The 3rd International Workshop on Science and Applications of SAR Polarimetry and Polarimetric Interferometry 22 26 January 2007 ESRIN Frascati, Italy Scientific

More information

Boosting. CAP5610: Machine Learning Instructor: Guo-Jun Qi

Boosting. CAP5610: Machine Learning Instructor: Guo-Jun Qi Boosting CAP5610: Machine Learning Instructor: Guo-Jun Qi Weak classifiers Weak classifiers Decision stump one layer decision tree Naive Bayes A classifier without feature correlations Linear classifier

More information

Multitemporal RADARSAT 2 Fine Beam Polarimetric SAR for Urban Land Cover Mapping

Multitemporal RADARSAT 2 Fine Beam Polarimetric SAR for Urban Land Cover Mapping Multitemporal RADARSAT 2 Fine Beam Polarimetric SAR for Urban Land Cover Mapping Yifang Ban & Xin Niu KTH Royal Institute of Technology Stockholm, Sweden Introduction Urban represents one of the most dynamic

More information

THE THEMATIC INFORMATION EXTRACTION FROM POLINSAR DATA FOR URBAN PLANNING AND MANAGEMENT

THE THEMATIC INFORMATION EXTRACTION FROM POLINSAR DATA FOR URBAN PLANNING AND MANAGEMENT THE THEMATIC INFORMATION EXTRACTION FROM POLINSAR DATA FOR URBAN PLANNING AND MANAGEMENT D.Amarsaikhan a, *, M.Sato b, M.Ganzorig a a Institute of Informatics and RS, Mongolian Academy of Sciences, av.enkhtaivan-54b,

More information

Advanced SAR 2 Polarimetry

Advanced SAR 2 Polarimetry Advanced SAR Polarimetry Eric POTTIER Monday 3 September, Lecture D1Lb5-3/9/7 Lecture D1Lb5- Advanced SAR - Polarimetry Eric POTTIER 1 $y RADAR POLARIMETRY $x r Ezt (, ) $z Radar Polarimetry (Polar : polarisation

More information

An Introduction to PolSAR-Ap: Exploitation of Fully Polarimetric SAR Data for Application Demonstration

An Introduction to PolSAR-Ap: Exploitation of Fully Polarimetric SAR Data for Application Demonstration An Introduction to PolSAR-Ap: Exploitation of Fully Polarimetric SAR Data for Application Demonstration Irena Hajnsek, Matteo Pardini, Kostas Papathanassiou, Shane Cloude, Juan M. Lopez-Sanchez, David

More information

URBAN MAPPING AND CHANGE DETECTION

URBAN MAPPING AND CHANGE DETECTION URBAN MAPPING AND CHANGE DETECTION Sebastian van der Linden with contributions from Akpona Okujeni Humboldt-Unveristät zu Berlin, Germany Introduction Introduction The urban millennium Source: United Nations,

More information

Study and Applications of POLSAR Data Time-Frequency Correlation Properties

Study and Applications of POLSAR Data Time-Frequency Correlation Properties Study and Applications of POLSAR Data Time-Frequency Correlation Properties L. Ferro-Famil 1, A. Reigber 2 and E. Pottier 1 1 University of Rennes 1, Institute of Electronics and Telecommunications of

More information

A New Model-Based Scattering Power Decomposition for Polarimetric SAR and Its Application in Analyzing Post-Tsunami Effects

A New Model-Based Scattering Power Decomposition for Polarimetric SAR and Its Application in Analyzing Post-Tsunami Effects A New Model-Based Scattering Power Decomposition for Polarimetric SAR and Its Application in Analyzing Post-Tsunami Effects Yi Cui, Yoshio Yamaguchi Niigata University, Japan Background (1/5) POLSAR data

More information

SAN FRANCISCO BAY. L-band 1988 AIRSAR. DC8 P, L, C-Band (Quad) Microwaves and Radar Institute, Wolfgang Keydel

SAN FRANCISCO BAY. L-band 1988 AIRSAR. DC8 P, L, C-Band (Quad) Microwaves and Radar Institute, Wolfgang Keydel SAN FRANCISCO BAY L-band 1988 AIRSAR DC8 P, L, C-Band (Quad) TARGET GENERATORS HH+VV T11=2A0 HV T33=B0-B HH-VV T22=B0+B TARGET GENERATORS Sinclair Color Coding HH HV VV Pauli Color Coding HH+VV T11=2A0

More information

Soil moisture retrieval over periodic surfaces using PolSAR data

Soil moisture retrieval over periodic surfaces using PolSAR data Soil moisture retrieval over periodic surfaces using PolSAR data Sandrine DANIEL Sophie ALLAIN Laurent FERRO-FAMIL Eric POTTIER IETR Laboratory, UMR CNRS 6164, University of Rennes1, France Contents Soil

More information

Contemporary Data Collection and Spatial Information Management Techniques to support Good Land Policies

Contemporary Data Collection and Spatial Information Management Techniques to support Good Land Policies Contemporary Data Collection and Spatial Information Management Techniques to support Good Land Policies Ch. Ioannidis Associate Professor FIG Commission 3 Workshop Paris, 25-28 October 2011 Introduction

More information

8. Classification and Pattern Recognition

8. Classification and Pattern Recognition 8. Classification and Pattern Recognition 1 Introduction: Classification is arranging things by class or category. Pattern recognition involves identification of objects. Pattern recognition can also be

More information

POLARIMETRIC SAR MODEL FOR SOIL MOISTURE ESTIMATION OVER VINEYARDS AT C-BAND

POLARIMETRIC SAR MODEL FOR SOIL MOISTURE ESTIMATION OVER VINEYARDS AT C-BAND Progress In Electromagnetics Research, Vol. 142, 639 665, 213 POLARIMETRIC SAR MODEL FOR SOIL MOISTURE ESTIMATION OVER VINEYARDS AT C-BAND J. David Ballester-Berman *, Fernando Vicente-Guijalba, and Juan

More information

High Dimensional Discriminant Analysis

High Dimensional Discriminant Analysis High Dimensional Discriminant Analysis Charles Bouveyron LMC-IMAG & INRIA Rhône-Alpes Joint work with S. Girard and C. Schmid ASMDA Brest May 2005 Introduction Modern data are high dimensional: Imagery:

More information

Snow property extraction based on polarimetry and differential SAR interferometry

Snow property extraction based on polarimetry and differential SAR interferometry Snow property extraction based on polarimetry and differential SAR interferometry S. Leinß, I. Hajnsek Earth Observation and Remote Sensing, Institute of Enviromental Science, ETH Zürich TerraSAR X and

More information

Spectral and Spatial Methods for the Classification of Urban Remote Sensing Data

Spectral and Spatial Methods for the Classification of Urban Remote Sensing Data Spectral and Spatial Methods for the Classification of Urban Remote Sensing Data Mathieu Fauvel gipsa-lab/dis, Grenoble Institute of Technology - INPG - FRANCE Department of Electrical and Computer Engineering,

More information

LAND COVER CLASSIFICATION BASED ON SAR DATA IN SOUTHEAST CHINA

LAND COVER CLASSIFICATION BASED ON SAR DATA IN SOUTHEAST CHINA LAND COVER CLASSIFICATION BASED ON SAR DATA IN SOUTHEAST CHINA Mr. Feilong Ling, Dr. Xiaoqin Wang, Mr.Xiaoming Shi Fuzhou University, Level 13, Science Building,No.53 Gongye Rd., 35, Fuzhou, China Email:

More information

Comparison between Multitemporal and Polarimetric SAR Data for Land Cover Classification

Comparison between Multitemporal and Polarimetric SAR Data for Land Cover Classification Downloaded from orbit.dtu.dk on: Sep 19, 2018 Comparison between Multitemporal and Polarimetric SAR Data for Land Cover Classification Skriver, Henning Published in: Geoscience and Remote Sensing Symposium,

More information

A Family of Distribution-Entropy MAP Speckle Filters for Polarimetric SAR Data, and for Single or Multi-Channel Detected and Complex SAR Images

A Family of Distribution-Entropy MAP Speckle Filters for Polarimetric SAR Data, and for Single or Multi-Channel Detected and Complex SAR Images A Family of Distribution-Entropy MAP Specle Filters for Polarimetric SAR Data, and for Single or Multi-Channel Detected and Complex SAR Images Edmond NEZRY and Francis YAKAM-SIMEN PRIVATEERS N.V., Private

More information

Airborne Holographic SAR Tomography at L- and P-band

Airborne Holographic SAR Tomography at L- and P-band Airborne Holographic SAR Tomography at L- and P-band O. Ponce, A. Reigber and A. Moreira. Microwaves and Radar Institute (HR), German Aerospace Center (DLR). 1 Outline Introduction to 3-D SAR Holographic

More information

BUILDING HEIGHT ESTIMATION USING MULTIBASELINE L-BAND SAR DATA AND POLARIMETRIC WEIGHTED SUBSPACE FITTING METHODS

BUILDING HEIGHT ESTIMATION USING MULTIBASELINE L-BAND SAR DATA AND POLARIMETRIC WEIGHTED SUBSPACE FITTING METHODS BUILDING HEIGHT ESTIMATION USING MULTIBASELINE L-BAND SAR DATA AND POLARIMETRIC WEIGHTED SUBSPACE FITTING METHODS Yue Huang, Laurent Ferro-Famil University of Rennes 1, Institute of Telecommunication and

More information

LAND COVER CLASSIFICATION OF PALSAR IMAGES BY KNOWLEDGE BASED DECISION TREE CLASSI- FIER AND SUPERVISED CLASSIFIERS BASED ON SAR OBSERVABLES

LAND COVER CLASSIFICATION OF PALSAR IMAGES BY KNOWLEDGE BASED DECISION TREE CLASSI- FIER AND SUPERVISED CLASSIFIERS BASED ON SAR OBSERVABLES Progress In Electromagnetics Research B, Vol. 30, 47 70, 2011 LAND COVER CLASSIFICATION OF PALSAR IMAGES BY KNOWLEDGE BASED DECISION TREE CLASSI- FIER AND SUPERVISED CLASSIFIERS BASED ON SAR OBSERVABLES

More information

CHAPTER-7 INTERFEROMETRIC ANALYSIS OF SPACEBORNE ENVISAT-ASAR DATA FOR VEGETATION CLASSIFICATION

CHAPTER-7 INTERFEROMETRIC ANALYSIS OF SPACEBORNE ENVISAT-ASAR DATA FOR VEGETATION CLASSIFICATION 147 CHAPTER-7 INTERFEROMETRIC ANALYSIS OF SPACEBORNE ENVISAT-ASAR DATA FOR VEGETATION CLASSIFICATION 7.1 INTRODUCTION: Interferometric synthetic aperture radar (InSAR) is a rapidly evolving SAR remote

More information

General Four-Component Scattering Power Decomposition with Unitary Transformation of Coherency Matrix

General Four-Component Scattering Power Decomposition with Unitary Transformation of Coherency Matrix 1 General Four-Component Scattering Power Decomposition with Unitary Transformation of Coherency Matrix Gulab Singh, Member, IEEE, Yoshio Yamaguchi, Fellow, IEEE and Sang-Eun Park, Member, IEEE Abstract

More information

Machine learning for pervasive systems Classification in high-dimensional spaces

Machine learning for pervasive systems Classification in high-dimensional spaces Machine learning for pervasive systems Classification in high-dimensional spaces Department of Communications and Networking Aalto University, School of Electrical Engineering stephan.sigg@aalto.fi Version

More information

Sub-pixel regional land cover mapping. with MERIS imagery

Sub-pixel regional land cover mapping. with MERIS imagery Sub-pixel regional land cover mapping with MERIS imagery R. Zurita Milla, J.G.P.W. Clevers and M. E. Schaepman Centre for Geo-information Wageningen University 29th September 2005 Overview Land Cover MERIS

More information

Features for Landcover Classification of Fully Polarimetric SAR Data

Features for Landcover Classification of Fully Polarimetric SAR Data Features for Landcover Classification of Fully Polarimetric SAR Data Jorge V. Geaga ABSTRACT We have previously shown that Stokes eigenvectors can be numerically extracted from the Kennaugh(Stokes matrices

More information

Application of Bootstrap Techniques for the Estimation of Target Decomposition Parameters in RADAR Polarimetry

Application of Bootstrap Techniques for the Estimation of Target Decomposition Parameters in RADAR Polarimetry Application of Bootstrap Techniques for the Estimation of Target Decomposition Parameters in RADAR Polarimetry Samuel Foucher Research & Development Dept Computer Research Institute of Montreal Montreal,

More information

Global Scene Representations. Tilke Judd

Global Scene Representations. Tilke Judd Global Scene Representations Tilke Judd Papers Oliva and Torralba [2001] Fei Fei and Perona [2005] Labzebnik, Schmid and Ponce [2006] Commonalities Goal: Recognize natural scene categories Extract features

More information

THE OBJECTIVE of the incoherent target decomposition

THE OBJECTIVE of the incoherent target decomposition IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, VOL. 45, NO. 1, JANUARY 2007 73 Target Scattering Decomposition in Terms of Roll-Invariant Target Parameters Ridha Touzi, Member, IEEE Abstract The Kennaugh

More information

Rice Monitoring using Simulated Compact SAR. Kun Li, Yun Shao Institute of Remote Sensing and Digital Earth

Rice Monitoring using Simulated Compact SAR. Kun Li, Yun Shao Institute of Remote Sensing and Digital Earth Rice Monitoring using Simulated Compact SAR Kun Li, Yun Shao Institute of Remote Sensing and Digital Earth Outlines Introduction Test site and data Results Rice type discrimination Rice phenology retrieval

More information

Model based forest height estimation with ALOS/PalSAR: A first study.

Model based forest height estimation with ALOS/PalSAR: A first study. Model based forest height estimation with ALOS/PalSAR: A first study. K.P. Papathanassiou*, I. Hajnsek*, T.Mette*, S.R. Cloude** and A. Moreira* * (DLR) (DLR-HR) Oberpfaffenhofen, Germany ** AEL Consultants

More information

Multitemporal Spaceborne Polarimetric SAR Data for Urban Land Cover Mapping

Multitemporal Spaceborne Polarimetric SAR Data for Urban Land Cover Mapping Multitemporal Spaceborne Polarimetric SAR Data for Urban Land Cover Mapping Xin Niu Feburary 2011 TRITA SoM 2011-05 ISSN 1653-6126 ISRN KTH/SoM/11-05/SE ISBN 978-91-7415-909-7 Xin Niu TRITA SoM 2011-05

More information

K&C Phase IV Status Report: Land Cover and Change in Papua New Guinea

K&C Phase IV Status Report: Land Cover and Change in Papua New Guinea K&C Phase IV Status Report: Land Cover and Change in Papua New Guinea Mark L. Williams Anthony K. Milne Anthea L. Mitchell Tropics in particular benefit from SAR because of cloud cover, and SAR is sensitive

More information

Analysis of the Temporal Behavior of Coherent Scatterers (CSs) in ALOS PalSAR Data

Analysis of the Temporal Behavior of Coherent Scatterers (CSs) in ALOS PalSAR Data Analysis of the Temporal Behavior of Coherent Scatterers (CSs) in ALOS PalSAR Data L. Marotti, R. Zandona-Schneider & K.P. Papathanassiou German Aerospace Center (DLR) Microwaves and Radar Institute0 PO.BOX

More information

THE PYLA 2001 EXPERIMENT : EVALUATION OF POLARIMETRIC RADAR CAPABILITIES OVER A FORESTED AREA

THE PYLA 2001 EXPERIMENT : EVALUATION OF POLARIMETRIC RADAR CAPABILITIES OVER A FORESTED AREA THE PYLA 2001 EXPERIMENT : EVALUATION OF POLARIMETRIC RADAR CAPABILITIES OVER A FORESTED AREA M. Dechambre 1, S. Le Hégarat 1, S. Cavelier 1, P. Dreuillet 2, I. Champion 3 1 CETP IPSL (CNRS / Université

More information

Urban Mapping. Sebastian van der Linden, Akpona Okujeni, Franz Schug 11/09/2018

Urban Mapping. Sebastian van der Linden, Akpona Okujeni, Franz Schug 11/09/2018 Urban Mapping Sebastian van der Linden, Akpona Okujeni, Franz Schug 11/09/2018 Introduction to urban remote sensing Introduction The urban millennium Source: United Nations, 2014 Urban areas mark extremes

More information

Incorporating detractors into SVM classification

Incorporating detractors into SVM classification Incorporating detractors into SVM classification AGH University of Science and Technology 1 2 3 4 5 (SVM) SVM - are a set of supervised learning methods used for classification and regression SVM maximal

More information

Combination of Microwave and Optical Remote Sensing in Land Cover Mapping

Combination of Microwave and Optical Remote Sensing in Land Cover Mapping Combination of Microwave and Optical Remote Sensing in Land Cover Mapping Key words: microwave and optical remote sensing; land cover; mapping. SUMMARY Land cover map mapping of various types use conventional

More information

c 4, < y 2, 1 0, otherwise,

c 4, < y 2, 1 0, otherwise, Fundamentals of Big Data Analytics Univ.-Prof. Dr. rer. nat. Rudolf Mathar Problem. Probability theory: The outcome of an experiment is described by three events A, B and C. The probabilities Pr(A) =,

More information

Remote Sensing Applications for Land/Atmosphere: Earth Radiation Balance

Remote Sensing Applications for Land/Atmosphere: Earth Radiation Balance Remote Sensing Applications for Land/Atmosphere: Earth Radiation Balance - Introduction - Deriving surface energy balance fluxes from net radiation measurements - Estimation of surface net radiation from

More information

Probabilistic Machine Learning. Industrial AI Lab.

Probabilistic Machine Learning. Industrial AI Lab. Probabilistic Machine Learning Industrial AI Lab. Probabilistic Linear Regression Outline Probabilistic Classification Probabilistic Clustering Probabilistic Dimension Reduction 2 Probabilistic Linear

More information

Classification Techniques with Applications in Remote Sensing

Classification Techniques with Applications in Remote Sensing Classification Techniques with Applications in Remote Sensing Hunter Glanz California Polytechnic State University San Luis Obispo November 1, 2017 Glanz Land Cover Classification November 1, 2017 1 /

More information

KNOWLEDGE-BASED CLASSIFICATION OF LAND COVER FOR THE QUALITY ASSESSEMENT OF GIS DATABASE. Israel -

KNOWLEDGE-BASED CLASSIFICATION OF LAND COVER FOR THE QUALITY ASSESSEMENT OF GIS DATABASE. Israel - KNOWLEDGE-BASED CLASSIFICATION OF LAND COVER FOR THE QUALITY ASSESSEMENT OF GIS DATABASE Ammatzia Peled a,*, Michael Gilichinsky b a University of Haifa, Department of Geography and Environmental Studies,

More information

GLOBAL FOREST CLASSIFICATION FROM TANDEM-X INTERFEROMETRIC DATA: POTENTIALS AND FIRST RESULTS

GLOBAL FOREST CLASSIFICATION FROM TANDEM-X INTERFEROMETRIC DATA: POTENTIALS AND FIRST RESULTS GLOBAL FOREST CLASSIFICATION FROM TANDEM-X INTERFEROMETRIC DATA: POTENTIALS AND FIRST RESULTS Michele Martone, Paola Rizzoli, Benjamin Bräutigam, Gerhard Krieger Microwaves and Radar Institute German Aerospace

More information

Support Vector Machine (continued)

Support Vector Machine (continued) Support Vector Machine continued) Overlapping class distribution: In practice the class-conditional distributions may overlap, so that the training data points are no longer linearly separable. We need

More information

High Dimensional Discriminant Analysis

High Dimensional Discriminant Analysis High Dimensional Discriminant Analysis Charles Bouveyron LMC-IMAG & INRIA Rhône-Alpes Joint work with S. Girard and C. Schmid High Dimensional Discriminant Analysis - Lear seminar p.1/43 Introduction High

More information

Snowfall Detection Using ATMS Measurements

Snowfall Detection Using ATMS Measurements Snowfall Detection Using ATMS Measurements Cezar Kongoli, Huan Meng, Ralph Ferraro and Jun Dong CICS/ESSIC, University of Maryland and NOAA/NESDIS/STAR Nov. 7, 2013 CICS-MD Science Meeting AMSU Heritage

More information

PATTERN RECOGNITION AND MACHINE LEARNING

PATTERN RECOGNITION AND MACHINE LEARNING PATTERN RECOGNITION AND MACHINE LEARNING Slide Set 3: Detection Theory January 2018 Heikki Huttunen heikki.huttunen@tut.fi Department of Signal Processing Tampere University of Technology Detection theory

More information

Introduction to Machine Learning Midterm Exam

Introduction to Machine Learning Midterm Exam 10-701 Introduction to Machine Learning Midterm Exam Instructors: Eric Xing, Ziv Bar-Joseph 17 November, 2015 There are 11 questions, for a total of 100 points. This exam is open book, open notes, but

More information

New Simple Decomposition Technique for Polarimetric SAR Images

New Simple Decomposition Technique for Polarimetric SAR Images Korean Journal of Remote Sensing, Vol.26, No.1, 2010, pp.1~7 New Simple Decomposition Technique for Polarimetric SAR Images Kyung-Yup Lee and Yisok Oh Department of Electronic Information and Communication

More information

What is semi-supervised learning?

What is semi-supervised learning? What is semi-supervised learning? In many practical learning domains, there is a large supply of unlabeled data but limited labeled data, which can be expensive to generate text processing, video-indexing,

More information

Classification CE-717: Machine Learning Sharif University of Technology. M. Soleymani Fall 2012

Classification CE-717: Machine Learning Sharif University of Technology. M. Soleymani Fall 2012 Classification CE-717: Machine Learning Sharif University of Technology M. Soleymani Fall 2012 Topics Discriminant functions Logistic regression Perceptron Generative models Generative vs. discriminative

More information

Perception: objects in the environment

Perception: objects in the environment Zsolt Vizi, Ph.D. 2018 Self-driving cars Sensor fusion: one categorization Type 1: low-level/raw data fusion combining several sources of raw data to produce new data that is expected to be more informative

More information

Machine Learning (CSE 446): Learning as Minimizing Loss; Least Squares

Machine Learning (CSE 446): Learning as Minimizing Loss; Least Squares Machine Learning (CSE 446): Learning as Minimizing Loss; Least Squares Sham M Kakade c 2018 University of Washington cse446-staff@cs.washington.edu 1 / 13 Review 1 / 13 Alternate View of PCA: Minimizing

More information

EMPIRICAL ESTIMATION OF VEGETATION PARAMETERS USING MULTISENSOR DATA FUSION

EMPIRICAL ESTIMATION OF VEGETATION PARAMETERS USING MULTISENSOR DATA FUSION EMPIRICAL ESTIMATION OF VEGETATION PARAMETERS USING MULTISENSOR DATA FUSION Franz KURZ and Olaf HELLWICH Chair for Photogrammetry and Remote Sensing Technische Universität München, D-80290 Munich, Germany

More information

CLASSIFICATION, decomposition, and modeling of polarimetric

CLASSIFICATION, decomposition, and modeling of polarimetric IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, VOL. 36, NO. 3, MAY 1998 963 A Three-Component Scattering Model for Polarimetric SAR Data Anthony Freeman, Senior Member, IEEE, Stephen L. Durden Abstract

More information

UNIVERSITY of PENNSYLVANIA CIS 520: Machine Learning Final, Fall 2013

UNIVERSITY of PENNSYLVANIA CIS 520: Machine Learning Final, Fall 2013 UNIVERSITY of PENNSYLVANIA CIS 520: Machine Learning Final, Fall 2013 Exam policy: This exam allows two one-page, two-sided cheat sheets; No other materials. Time: 2 hours. Be sure to write your name and

More information

TEXTURE ANALSYS OF SAR IMAGERY IN THE SPACE-SCALE-POLARIZATION DOMAIN BY WAVELET FRAMES

TEXTURE ANALSYS OF SAR IMAGERY IN THE SPACE-SCALE-POLARIZATION DOMAIN BY WAVELET FRAMES TEXTURE ANALSYS OF SAR IMAGERY IN THE SPACE-SCALE-POLARIZATION DOMAIN BY WAVELET FRAMES G. De Grandi 1, J. Kropacek 1, A. Gambardella 2, R.M. Lucas 3, M. Migliaccio 2 Joint Research Centre 21027, Ispra

More information

Convex Optimization and Support Vector Machine

Convex Optimization and Support Vector Machine Convex Optimization and Support Vector Machine Problem 0. Consider a two-class classification problem. The training data is L n = {(x 1, t 1 ),..., (x n, t n )}, where each t i { 1, 1} and x i R p. We

More information

Towards Maximum Geometric Margin Minimum Error Classification

Towards Maximum Geometric Margin Minimum Error Classification THE SCIENCE AND ENGINEERING REVIEW OF DOSHISHA UNIVERSITY, VOL. 50, NO. 3 October 2009 Towards Maximum Geometric Margin Minimum Error Classification Kouta YAMADA*, Shigeru KATAGIRI*, Erik MCDERMOTT**,

More information

Machine Learning and Deep Learning! Vincent Lepetit!

Machine Learning and Deep Learning! Vincent Lepetit! Machine Learning and Deep Learning!! Vincent Lepetit! 1! What is Machine Learning?! 2! Hand-Written Digit Recognition! 2 9 3! Hand-Written Digit Recognition! Formalization! 0 1 x = @ A Images are 28x28

More information

Urban land cover and land use extraction from Very High Resolution remote sensing imagery

Urban land cover and land use extraction from Very High Resolution remote sensing imagery Urban land cover and land use extraction from Very High Resolution remote sensing imagery Mengmeng Li* 1, Alfred Stein 1, Wietske Bijker 1, Kirsten M.de Beurs 2 1 Faculty of Geo-Information Science and

More information

EE/Ge 157 b. Week 2. Polarimetric Synthetic Aperture Radar (2)

EE/Ge 157 b. Week 2. Polarimetric Synthetic Aperture Radar (2) EE/Ge 157 b Week 2 Polarimetric Synthetic Aperture Radar (2) COORDINATE SYSTEMS All matrices and vectors shown in this package are measured using the backscatter alignment coordinate system. This system

More information

Transactions on Information and Communications Technologies vol 18, 1998 WIT Press, ISSN

Transactions on Information and Communications Technologies vol 18, 1998 WIT Press,  ISSN Ready-to-use GIS information from remotely sensed data G. Sylos Labini*, S. Samarelli*, G. Pasquariello^ G. Nico*, A. Refice* & J. Bequignon ' Planetek Italia, Tecnopolis, 70010 Valenzano, Bari, Italy

More information

The Perceptron. Volker Tresp Summer 2016

The Perceptron. Volker Tresp Summer 2016 The Perceptron Volker Tresp Summer 2016 1 Elements in Learning Tasks Collection, cleaning and preprocessing of training data Definition of a class of learning models. Often defined by the free model parameters

More information

Analysis of High Resolution Multi-frequency, Multipolarimetric and Interferometric Airborne SAR Data for Hydrologic Model Parameterization

Analysis of High Resolution Multi-frequency, Multipolarimetric and Interferometric Airborne SAR Data for Hydrologic Model Parameterization Analysis of High Resolution Multi-frequency, Multipolarimetric and Interferometric Airborne SAR Data for Hydrologic Model Parameterization Martin Herold 1, Volker Hochschild 2 1 Remote Sensing Research

More information

MONITORING OF GLACIAL CHANGE IN THE HEAD OF THE YANGTZE RIVER FROM 1997 TO 2007 USING INSAR TECHNIQUE

MONITORING OF GLACIAL CHANGE IN THE HEAD OF THE YANGTZE RIVER FROM 1997 TO 2007 USING INSAR TECHNIQUE MONITORING OF GLACIAL CHANGE IN THE HEAD OF THE YANGTZE RIVER FROM 1997 TO 2007 USING INSAR TECHNIQUE Hong an Wu a, *, Yonghong Zhang a, Jixian Zhang a, Zhong Lu b, Weifan Zhong a a Chinese Academy of

More information

Course in Data Science

Course in Data Science Course in Data Science About the Course: In this course you will get an introduction to the main tools and ideas which are required for Data Scientist/Business Analyst/Data Analyst. The course gives an

More information

PUBLICATIONS. Radio Science. Impact of cross-polarization isolation on polarimetric target decomposition and target detection

PUBLICATIONS. Radio Science. Impact of cross-polarization isolation on polarimetric target decomposition and target detection PUBLICATIONS RESEARCH ARTICLE Key Points: Prior studies are on calibration; we evaluate its impact from users perspective Impact on polarimetric target decomposition is analyzed, and 25 db is concluded

More information

Classification of High Spatial Resolution Remote Sensing Images Based on Decision Fusion

Classification of High Spatial Resolution Remote Sensing Images Based on Decision Fusion Journal of Advances in Information Technology Vol. 8, No. 1, February 2017 Classification of High Spatial Resolution Remote Sensing Images Based on Decision Fusion Guizhou Wang Institute of Remote Sensing

More information

OBJECT DETECTION AND RECOGNITION IN DIGITAL IMAGES

OBJECT DETECTION AND RECOGNITION IN DIGITAL IMAGES OBJECT DETECTION AND RECOGNITION IN DIGITAL IMAGES THEORY AND PRACTICE Bogustaw Cyganek AGH University of Science and Technology, Poland WILEY A John Wiley &. Sons, Ltd., Publication Contents Preface Acknowledgements

More information

A Multi-component Decomposition Method for Polarimetric SAR Data

A Multi-component Decomposition Method for Polarimetric SAR Data Chinese Journal of Electronics Vol.26, No.1, Jan. 2017 A Multi-component Decomposition Method for Polarimetric SAR Data WEI Jujie 1, ZHAO Zheng 1, YU Xiaoping 2 and LU Lijun 1 (1. Chinese Academy of Surveying

More information

The Potential of High Resolution Satellite Interferometry for Monitoring Enhanced Oil Recovery

The Potential of High Resolution Satellite Interferometry for Monitoring Enhanced Oil Recovery The Potential of High Resolution Satellite Interferometry for Monitoring Enhanced Oil Recovery Urs Wegmüller a Lutz Petrat b Karsten Zimmermann c Issa al Quseimi d 1 Introduction Over the last years land

More information

RADAR BACKSCATTER AND COHERENCE INFORMATION SUPPORTING HIGH QUALITY URBAN MAPPING

RADAR BACKSCATTER AND COHERENCE INFORMATION SUPPORTING HIGH QUALITY URBAN MAPPING RADAR BACKSCATTER AND COHERENCE INFORMATION SUPPORTING HIGH QUALITY URBAN MAPPING Peter Fischer (1), Zbigniew Perski ( 2), Stefan Wannemacher (1) (1)University of Applied Sciences Trier, Informatics Department,

More information

Pattern Recognition and Machine Learning

Pattern Recognition and Machine Learning Christopher M. Bishop Pattern Recognition and Machine Learning ÖSpri inger Contents Preface Mathematical notation Contents vii xi xiii 1 Introduction 1 1.1 Example: Polynomial Curve Fitting 4 1.2 Probability

More information

Fitting a two-component scattering model to polarimetric SAR data from forests

Fitting a two-component scattering model to polarimetric SAR data from forests Fitting a two-component scattering model to polarimetric SAR data from forests A. Freeman, Fellow, IEEE Jet Propulsion Laboratory, California Institute of Technology 4800 Oak Grove Drive, Pasadena, CA

More information

Archimer

Archimer Please note that this is an author-produced PDF of an article accepted for publication following peer review. The definitive publisher-authenticated version is available on the publisher Web site Ieee

More information

COMS 4771 Lecture Boosting 1 / 16

COMS 4771 Lecture Boosting 1 / 16 COMS 4771 Lecture 12 1. Boosting 1 / 16 Boosting What is boosting? Boosting: Using a learning algorithm that provides rough rules-of-thumb to construct a very accurate predictor. 3 / 16 What is boosting?

More information

Possible Use of Synthetic Aperture Radar Images in IACS

Possible Use of Synthetic Aperture Radar Images in IACS Possible Use of Synthetic Aperture Radar Images in IACS 51st Panta Rhei Conference Hungary - April 2017. György Surek Zoltán Friedl - Gizella Nádor - Mátyás Rada - Anikó Kulcsár - Irén Hubik Government

More information

GEO Joint Experiment for Crop Assessment and Monitoring (JECAM): 2014 Site Progress Report

GEO Joint Experiment for Crop Assessment and Monitoring (JECAM): 2014 Site Progress Report GEO Joint Experiment for Crop Assessment and Monitoring (JECAM): JECAM Test Site Name: China - Guangdong 2014 Site Progress Report Team Leader and Members: Prof Wu Bingfang (Leader), Jiratiwan Kruasilp,

More information

The Application of Extreme Learning Machine based on Gaussian Kernel in Image Classification

The Application of Extreme Learning Machine based on Gaussian Kernel in Image Classification he Application of Extreme Learning Machine based on Gaussian Kernel in Image Classification Weijie LI, Yi LIN Postgraduate student in College of Survey and Geo-Informatics, tongji university Email: 1633289@tongji.edu.cn

More information

Support Vector Machines. CAP 5610: Machine Learning Instructor: Guo-Jun QI

Support Vector Machines. CAP 5610: Machine Learning Instructor: Guo-Jun QI Support Vector Machines CAP 5610: Machine Learning Instructor: Guo-Jun QI 1 Linear Classifier Naive Bayes Assume each attribute is drawn from Gaussian distribution with the same variance Generative model:

More information

Midterm. Introduction to Machine Learning. CS 189 Spring You have 1 hour 20 minutes for the exam.

Midterm. Introduction to Machine Learning. CS 189 Spring You have 1 hour 20 minutes for the exam. CS 189 Spring 2013 Introduction to Machine Learning Midterm You have 1 hour 20 minutes for the exam. The exam is closed book, closed notes except your one-page crib sheet. Please use non-programmable calculators

More information

Jeff Howbert Introduction to Machine Learning Winter

Jeff Howbert Introduction to Machine Learning Winter Classification / Regression Support Vector Machines Jeff Howbert Introduction to Machine Learning Winter 2012 1 Topics SVM classifiers for linearly separable classes SVM classifiers for non-linearly separable

More information

Deep Feedforward Networks. Han Shao, Hou Pong Chan, and Hongyi Zhang

Deep Feedforward Networks. Han Shao, Hou Pong Chan, and Hongyi Zhang Deep Feedforward Networks Han Shao, Hou Pong Chan, and Hongyi Zhang Deep Feedforward Networks Goal: approximate some function f e.g., a classifier, maps input to a class y = f (x) x y Defines a mapping

More information

Bayesian Learning (II)

Bayesian Learning (II) Universität Potsdam Institut für Informatik Lehrstuhl Maschinelles Lernen Bayesian Learning (II) Niels Landwehr Overview Probabilities, expected values, variance Basic concepts of Bayesian learning MAP

More information

On the use of Matrix Information Geometry for Polarimetric SAR Image Classification

On the use of Matrix Information Geometry for Polarimetric SAR Image Classification On the use of Matrix Information Geometry for Polarimetric SAR Image Classification Pierre Formont 1,2,Jean-PhilippeOvarlez 1,andFrédéric Pascal 2 1 French Aerospace Lab, ONERA DEMR/TSI, France 2 E3S-SONDRA,

More information

Multivariate Statistics Summary and Comparison of Techniques. Multivariate Techniques

Multivariate Statistics Summary and Comparison of Techniques. Multivariate Techniques Multivariate Statistics Summary and Comparison of Techniques P The key to multivariate statistics is understanding conceptually the relationship among techniques with regards to: < The kinds of problems

More information

Does Modeling Lead to More Accurate Classification?

Does Modeling Lead to More Accurate Classification? Does Modeling Lead to More Accurate Classification? A Comparison of the Efficiency of Classification Methods Yoonkyung Lee* Department of Statistics The Ohio State University *joint work with Rui Wang

More information