IGARSS 2015 : JULY 26 –31, MILAN, ITALY

Slides:



Advertisements
Similar presentations
Principal Component Analysis Based on L1-Norm Maximization Nojun Kwak IEEE Transactions on Pattern Analysis and Machine Intelligence, 2008.
Advertisements

Spatial and Spectral Evaluation of Image Fusion Methods Sascha Klonus Manfred Ehlers Institute for Geoinformatics and Remote Sensing University of Osnabrück.
Ashwin Yerasi (University of Colorado)
Similarity Search for Adaptive Ellipsoid Queries Using Spatial Transformation Yasushi Sakurai (NTT Cyber Space Laboratories) Masatoshi Yoshikawa (Nara.
Face Recognition in Hyperspectral Images Z. Pan, G. Healey, M. Prasad and B. Tromberg University of California Published at IEEE Trans. on PAMI Vol 25,
A KLT-Based Approach for Occlusion Handling in Human Tracking Chenyuan Zhang, Jiu Xu, Axel Beaugendre and Satoshi Goto 2012 Picture Coding Symposium.
La Parguera Hyperspectral Image size (250x239x118) using Hyperion sensor. INTEREST POINTS FOR HYPERSPECTRAL IMAGES Amit Mukherjee 1, Badrinath Roysam 1,
Volkan Cevher, Marco F. Duarte, and Richard G. Baraniuk European Signal Processing Conference 2008.
Content-based Image Retrieval CE 264 Xiaoguang Feng March 14, 2002 Based on: J. Huang. Color-Spatial Image Indexing and Applications. Ph.D thesis, Cornell.
CF-3 Bank Hapoalim Jun-2001 Zvi Wiener Computational Finance.
USE OF LAPLACE APPROXIMATIONS TO SIGNIFICANTLY IMPROVE THE EFFICIENCY
FE-W EMBAF Zvi Wiener Financial Engineering.
A Design Method for MIMO Radar Frequency Hopping Codes Chun-Yang Chen and P. P. Vaidyanathan California Institute of Technology Electrical Engineering/DSP.
Quality Assessment of Roads in Colorado Based on Satellite Imagery April 7, 2014.
Forestry Department, Faculty of Natural Resources
Estimation Error and Portfolio Optimization Global Asset Allocation and Stock Selection Campbell R. Harvey Duke University, Durham, NC USA National Bureau.
U N I V E R S I T À D E G L I S T U D I D I M I L A N O C17 SC for Environmental Applications and Remote Sensing I M S C I A Soft Computing for Environmental.
Ryan Irwin Intelligent Electronics Systems Human and Systems Engineering Center for Advanced Vehicular Systems URL:
Clustering methods Course code: Pasi Fränti Speech & Image Processing Unit School of Computing University of Eastern Finland Joensuu,
Polynomial Chaos For Dynamical Systems Anatoly Zlotnik, Case Western Reserve University Mohamed Jardak, Florida State University.
Meta-optimization of the Extended Kalman filter’s parameters for improved feature extraction on hyper-temporal images. B.P. Salmon 1,2*, W. Kleynhans 1,2,
A New Subspace Approach for Supervised Hyperspectral Image Classification Jun Li 1,2, José M. Bioucas-Dias 2 and Antonio Plaza 1 1 Hyperspectral Computing.
Blue: Histogram of normalised deviation from “true” value; Red: Gaussian fit to histogram Presented at ESA Hyperspectral Workshop 2010, March 16-19, Frascati,
1 Physical Fluctuomatics 5th and 6th Probabilistic information processing by Gaussian graphical model Kazuyuki Tanaka Graduate School of Information Sciences,
ASPRS Annual Conference 2005, Baltimore, March Utilizing Multi-Resolution Image data vs. Pansharpened Image data for Change Detection V. Vijayaraj,
Dimensionality Reduction in Hyperspectral Image Analysis Using Independent Component Analysis Hongtao Du Feb 18, 2003.
Mapping shorelines to subpixel accuracy using Landsat imagery Ron Abileah (1), Stefano Vignudelli (2), and Andrea Scozzari (3) (1) jOmegak, San Carlos.
Stochastic Linear Programming by Series of Monte-Carlo Estimators Leonidas SAKALAUSKAS Institute of Mathematics&Informatics Vilnius, Lithuania
Improvement of Multi-bit Information Embedding Algorithm for Palette-Based Images Anu Aryal, Kazuma Motegi, Shoko Imaizumi and Naokazu Aoki Division of.
Estimating Water Optical Properties, Water Depth and Bottom Albedo Using High Resolution Satellite Imagery for Coastal Habitat Mapping S. C. Liew #, P.
Compressive Sensing for Multimedia Communications in Wireless Sensor Networks By: Wael BarakatRabih Saliba EE381K-14 MDDSP Literary Survey Presentation.
Spectral classification of WorldView-2 multi-angle sequence Atlanta city-model derived from a WorldView-2 multi-sequence acquisition N. Longbotham, C.
EE381K-14 MDDSP Literary Survey Presentation March 4th, 2008
References: [1]S.M. Smith et al. (2004) Advances in functional and structural MR image analysis and implementation in FSL. Neuroimage 23: [2]S.M.
Covariance Estimation For Markowitz Portfolio Optimization Ka Ki Ng Nathan Mullen Priyanka Agarwal Dzung Du Rezwanuzzaman Chowdhury 14/7/2010.
IGARSS 2011, Vancouver, Canada HYPERSPECTRAL UNMIXING USING A NOVEL CONVERSION MODEL Fereidoun A. Mianji, Member, IEEE, Shuang Zhou, Member, IEEE, Ye Zhang,
Bivariate Poisson regression models for automobile insurance pricing Lluís Bermúdez i Morata Universitat de Barcelona IME 2007 Piraeus, July.
Full-rank Gaussian modeling of convolutive audio mixtures applied to source separation Ngoc Q. K. Duong, Supervisor: R. Gribonval and E. Vincent METISS.
A NOVEL METHOD FOR COLOR FACE RECOGNITION USING KNN CLASSIFIER
Advanced Science and Technology Letters Vol.28 (EEC 2013), pp Histogram Equalization- Based Color Image.
Iterative K-Means Algorithm Based on Fisher Discriminant UNIVERSITY OF JOENSUU DEPARTMENT OF COMPUTER SCIENCE JOENSUU, FINLAND Mantao Xu to be presented.
Advanced Science and Technology Letters Vol.28 (EEC 2013), pp Fuzzy Technique for Color Quality Transformation.
Shadow Detection in Remotely Sensed Images Based on Self-Adaptive Feature Selection Jiahang Liu, Tao Fang, and Deren Li IEEE TRANSACTIONS ON GEOSCIENCE.
An Automatic Method for Selecting the Parameter of the RBF Kernel Function to Support Vector Machines Cheng-Hsuan Li 1,2 Chin-Teng.
VIIRS-derived Chlorophyll-a using the Ocean Color Index method SeungHyun Son 1,2 and Menghua Wang 1 1 NOAA/NESDIS/STAR, E/RA3, College Park, MD, USA 2.
Initial Display Alternatives and Scientific Visualization
Fuzzy type Image Fusion using hybrid DCT-FFT based Laplacian Pyramid Transform Authors: Rajesh Kumar Kakerda, Mahendra Kumar, Garima Mathur, R P Yadav,
Tae Young Kim and Myung jin Choi
An Image Database Retrieval Scheme Based Upon Multivariate Analysis and Data Mining Presented by C.C. Chang Dept. of Computer Science and Information.
Structure Similarity Index
Scatter-plot Based Blind Estimation of Mixed Noise Parameters
Early termination for tz search in hevc motion estimation
ROBUST SUBSPACE LEARNING FOR VISION AND GRAPHICS
High Performance Computing and Monte Carlo Methods
CSCE 2017 ICAI 2017 Las Vegas July. 17.
Content-based Image Retrieval
East China Normal University Fang Li
Ebrahim Bedeer*, Halim Yanikomeroglu*, and Mohamed Hossam Ahmed**
Estimation Error and Portfolio Optimization
Presented by Nagesh Adluru
Summary - end of term Lab Monday: 4 April return of assignments Lecture exam: 5 April, projects by end of term: April 6 Lecture evaluation.
Lecture 4 - Monte Carlo improvements via variance reduction techniques: antithetic sampling Antithetic variates: for any one path obtained by a gaussian.
第 四 章 VQ 加速運算與編碼表壓縮 4-.
SPOT National Mosaic Launch
Agustí Emperador, Oliver Carrillo, Manuel Rueda, Modesto Orozco 
Chapter 14 Monte Carlo Simulation
Low-Complexity Detection of M-ary PSK Faster-than-Nyquist Signaling
Estimation Error and Portfolio Optimization
Multivariate Statistics
Fig. 3 Forward model. Forward model. Summary of the resampled Monte Carlo simulations shown as histograms for epoch 1 (red), epoch 2 (green), and epoch.
Presentation transcript:

IGARSS 2015 : JULY 26 –31, 2015. MILAN, ITALY REMOTE SENSING : UNDERSTANDING THE EARTH FOR A SAFER WORLD FUSION OF MULTISPECTRAL SATELLITE IMAGE BY QUASI MONTE CARLO SAMPLING METHODS Mohamed KHIDER1, Soumya OURABIA1, Youcef SMARA1 1LTIR, Faculté d’Electronique et d’Informatique, Université des Sciences et de la Technologie Houari Boumedienne, B.P. 32 Bab Ezzouar, 16111, Algiers, Algeria. E-mail: mohamed.khider@ieee.org Introduction The present work proposes the study of satellite image fusion methods applied to ALSAT-2A, by introducing the pseudo and quasi-random Monte Carlo sampling PMC and QMC to reduce the computation time and also as a Pan Sharpening interpolation method, using three methods based on QMC sampling. Example : multispectral image, panchromatic at right QMC distribution. Diagram.1 combination of methods Diagram.2 Histogram matching between IHS Bands and QMC Fig.1 Fusion by Diagram 3 : direct estimation and right by simulated annealing. Fig.6 eigenvectors by QMC in red color. Histogram matching operation Fig.7 Fig.2 QMC norms positions using sorting. Fig.8 2 3 1 histogram matching : between band obtained by IHS and QMC positions of the PCA method. 4 6 5 Diagram.3 PCA interpolation by QMC with simulated annealing Fig.3 PCA QMC method, using simulated annealing , insufficient number of levels and Gamma. Fig.4 Fig.9 Conclusion In this paper, we have implemented differents Pansharpening methods based on QMC sampling, from this study, we have found that (1) it’s possible to diminish the computation time of the covariance matrix using QMC positions this reduces the computation time to 99%. (2) Ability to privilege the spatial or spectral quality with the use of QMC positions and the Euclidean distance between original spectra and those of the QMC positions after fusion, this allows us to increase the quality factor Qps, for this purpose the minimum distance is calculated by simulated annealing method. (3) Interpolation based on QMC positions and matching histograms indicate an improvement in fusion results. As perspectives, we propose the optimization of algorithms and the study of a bigger image database. A more important number of levels and Gamma. Pansharpening by method 3, on the right , result obtained with IHS Fig.5 Method Qwb Red Qwb Green Qwb Blue CC Red CC Green CC Blue Moy(Q) Moy(CC) Qps 1 0,6803 0,6704 0,7977 0,9485 0,9499 0,9010 0,7161 0,9331 0,6682 2 0,7851 0,7125 0,5507 0,9482 0,9558 0,9306 0,6827 0,9449 0,6451 3 0,8140 0,8323 0,8583 0,8963 0,8879 0,8204 0,8349 0,8682 0,7249 IHS 0,6986 0,6233 0,4452 0,9825 0,9861 0,9615 0,5891 0,9767 0,5754 BROVEY 0,2254 0,2217 0,2138 0,9818 0,9620 0,2203 0,2152 HCS 0,5730 0,5366 0,4642 0,9801 0,9850 0,9623 0,5246 0,9758 0,5119 HCS Smart 0,5733 0,5368 0,9800 0,9621 0,5248 0,9757 0,5120 PCA 0,6924 0,6555 0,7926 0,9486 0,9494 0,9025 0,7135 0,9335 0,6661 CN 0,7090 0,6169 0,4644 0,5968 0,5829 Gram Schmidt 0,2047 0,1997 0,1877 0,9302 0,9276 0,8908 0,1974 0,9162 0,1808 LMM 0,7758 0,7008 0,5593 0,9469 0,9546 0,9357 0,6786 0,9457 0,6418 LMVM 0,9208 0,9144 0,9089 0,8224 0,8250 0,8054 0,9147 0,8176 0,7479 GLP 0,6147 0,5979 0,5691 0,9911 0,9867 0,9770 0,5939 0,9849 0,5850 DWT 0,7386 0,6524 0,4703 0,9337 0,9311 0,8943 0,6204 0,9197 0,5707 C. Price 0,8522 0,8449 0,8472 0,8895 0,8846 0,8481 0,8754 0,7424 References [1] Hayes, B. : Excursions quasi-aléatoires. Pour la Science. n° 410. p 54-60. décembre 2011. [2] Xiaoqun Wang, 2001 : Variance reduction techniques and quasi-Monte Carlo methods. Journal of Computational and Applied Mathematics, 132, p 309-318. Elsevier. [3] Padwick C., Deskevich M., Pacifici F. and Smallwood S., 2010 : Worldview-2 PAN-Sharpening. ASPRS 2010 Annual Conference, San Diego, California, April 26-30, 2010. [4] Zhou Wang and Alan C. Bovik, 2002 : A Universal Image Quality Index. IEEE Signal Processing Letters. Vol XX, No Y. march 2002. [5] Paskov S.H. et Traub J.E, 1995 : Faster Valuation of Financial Derivatives. Journal of Portfolio Management. Vol 22. p 113-121. [6] Henri Faure, 2007 : Van der Corput sequences towards general (0,1)- sequences in base b.Journal de théorie des nombres de Bordeaux 19. p 125-140. [7] Manuel Bompard, 2011 : Modèles de substitution pour l’optimisation globale de forme en aérodynamique et méthode locale sans paramétrisation. Thèse Doctorat en Sciences. Université de Nice-Sophia Antipolis. [8] Niederreiter, H. 1992 : Random Number Generation and Quasi-Monte-Carlo Methods. CMBS-NSF, Vol.63. Philadelphia : SIAM. Table.1 Comparison of Pansharpening methods by using Qps factor.