Analysis of Hyperspectral Image Using Minimum Volume Transform (MVT) Ziv Waxman & Chen Vanunu Instructor: Mr. Oleg Kuybeda.

Slides:



Advertisements
Similar presentations
Solving LP Models Improving Search Special Form of Improving Search
Advertisements

1 Constraint operations: Simplification, Optimization and Implication.
Jeffrey W. Mirick, PhD. SPIE – Defense, Security, and Sensing Conference April 2010 Jeffrey W. Mirick, PhD. SPIE – Defense, Security, and Sensing.
Grey Level Enhancement Contrast stretching Linear mapping Non-linear mapping Efficient implementation of mapping algorithms Design of classes to support.
Dynamic Occlusion Analysis in Optical Flow Fields
How should we define corner points? Under any reasonable definition, point x should be considered a corner point x What is a corner point?
ECE 8443 – Pattern Recognition ECE 8423 – Adaptive Signal Processing Objectives: The FIR Adaptive Filter The LMS Adaptive Filter Stability and Convergence.
Extensions of wavelets
A Randomized Polynomial-Time Simplex Algorithm for Linear Programming Daniel A. Spielman, Yale Joint work with Jonathan Kelner, M.I.T.
Light Mixture Estimation for Spatially Varying White Balance
Design and Analysis of Algorithms
Uncalibrated Geometry & Stratification Sastry and Yang
1 Engineering Computation Part 4. 2 Enrique Castillo University of Cantabria An algorithm that permits solving many problems in Algebra. Applications.
Introduction of the intrinsic image. Intrinsic Images The method of Finlayson & Hordley ( 2001 ) Two assumptions 1. the camera ’ s sensors are sufficiently.
1 Introduction to Approximation Algorithms Lecture 15: Mar 5.
Digital Imaging and Remote Sensing Laboratory Real-World Stepwise Spectral Unmixing Daniel Newland Dr. John Schott Digital Imaging and Remote Sensing Laboratory.
Bootstrapping a Heteroscedastic Regression Model with Application to 3D Rigid Motion Evaluation Bogdan Matei Peter Meer Electrical and Computer Engineering.
Course: Advanced Algorithms CSG713, Fall 2008 CCIS Department, Northeastern University Dimitrios Kanoulas.
Handwritten Character Recognition using Hidden Markov Models Quantifying the marginal benefit of exploiting correlations between adjacent characters and.
Management and Cost Accounting, 6 th edition, ISBN © 2004 Colin Drury MANAGEMENT AND COST ACCOUNTING SIXTH EDITION COLIN DRURY.
Cost-Volume-Profit Analysis © 2012 Pearson Prentice Hall. All rights reserved.
Algebra 2 Chapter 3 Notes Systems of Linear Equalities and Inequalities Algebra 2 Chapter 3 Notes Systems of Linear Equalities and Inequalities.
Algebra 2 Chapter 3 Notes Systems of Linear Equalities and Inequalities Algebra 2 Chapter 3 Notes Systems of Linear Equalities and Inequalities.
Noise-Robust Spatial Preprocessing Prior to Endmember Extraction from Hyperspectral Data Gabriel Martín, Maciel Zortea and Antonio Plaza Hyperspectral.
Linear Programming Models Tran Van Hoai Faculty of Computer Science & Engineering HCMC University of Technology Tran Van Hoai.
-1- ICA Based Blind Adaptive MAI Suppression in DS-CDMA Systems Malay Gupta and Balu Santhanam SPCOM Laboratory Department of E.C.E. The University of.
WOOD 492 MODELLING FOR DECISION SUPPORT Lecture 3 Basics of the Simplex Algorithm.
Linear Programming Erasmus Mobility Program (24Apr2012) Pollack Mihály Engineering Faculty (PMMK) University of Pécs João Miranda
A New Method of Probability Density Estimation for Mutual Information Based Image Registration Ajit Rajwade, Arunava Banerjee, Anand Rangarajan. Dept.
IGARSS 2011, Vancouver, Canada HYPERSPECTRAL UNMIXING USING A NOVEL CONVERSION MODEL Fereidoun A. Mianji, Member, IEEE, Shuang Zhou, Member, IEEE, Ye Zhang,
Soham Uday Mehta. Linear Programming in 3 variables.
Endmember Extraction from Highly Mixed Data Using MVC-NMF Lidan Miao AICIP Group Meeting Apr. 6, 2006 Lidan Miao AICIP Group Meeting Apr. 6, 2006.
Color and Brightness Constancy Jim Rehg CS 4495/7495 Computer Vision Lecture 25 & 26 Wed Oct 18, 2002.
1  Problem: Consider a two class task with ω 1, ω 2   LINEAR CLASSIFIERS.
Review of Spectral Unmixing for Hyperspectral Imagery Lidan Miao Sept. 29, 2005.
Demosaicking for Multispectral Filter Array (MSFA)
Large-Scale Matrix Factorization with Missing Data under Additional Constraints Kaushik Mitra University of Maryland, College Park, MD Sameer Sheoreyy.
Mathematical Analysis of MaxEnt for Mixed Pixel Decomposition
Part 3. Linear Programming 3.2 Algorithm. General Formulation Convex function Convex region.
Feature Selction for SVMs J. Weston et al., NIPS 2000 오장민 (2000/01/04) Second reference : Mark A. Holl, Correlation-based Feature Selection for Machine.
Digital Image Processing Lecture 16: Segmentation: Detection of Discontinuities May 2, 2005 Prof. Charlene Tsai.
Comparative Analysis of Spectral Unmixing Algorithms Lidan Miao Nov. 10, 2005.
Chance Constrained Robust Energy Efficiency in Cognitive Radio Networks with Channel Uncertainty Yongjun Xu and Xiaohui Zhao College of Communication Engineering,
Intro. ANN & Fuzzy Systems Lecture 16. Classification (II): Practical Considerations.
Common Intersection of Half-Planes in R 2 2 PROBLEM (Common Intersection of half- planes in R 2 ) Given n half-planes H 1, H 2,..., H n in R 2 compute.
Morphological Image Processing
Computational Geometry
What is thermal noise? Thermal noise in the resistance of the signal source is the fundamental limit on achievable signal sensitivity is unavoidable, and.
Pixel Purity Index Assumes spectrally “pure” pixels are likely to correspond to “in scene” end members   For i = 1 to N Randomly generate a unit vector.
Deep Feedforward Networks
Modeling and Simulation CS 313
Hyperspectral Analysis Techniques
Orthogonal Subspace Projection - Matched Filter
Energy Preserving Non-linear Filters
The break signal in climate records: Random walk or random deviations
Two Models Representing World Features
Fundamentals of regression analysis
Hyperspectral Image preprocessing
Lecture 13: Spectral Mixture Analysis
What Is Spectral Imaging? An Introduction
Outline S. C. Zhu, X. Liu, and Y. Wu, “Exploring Texture Ensembles by Efficient Markov Chain Monte Carlo”, IEEE Transactions On Pattern Analysis And Machine.
3-3 Optimization with Linear Programming
Sensitivity ANALYSIS Sébastien Wagner (EUMETSAT) In collaboration with
Part 3. Linear Programming
Sparse Regression-based Hyperspectral Unmixing
What is the function of the graph? {applet}
Part 3. Linear Programming
Lecture 16. Classification (II): Practical Considerations
Presentation transcript:

Analysis of Hyperspectral Image Using Minimum Volume Transform (MVT) Ziv Waxman & Chen Vanunu Instructor: Mr. Oleg Kuybeda

Objectives: Testing the MVT algorithm as a tool of analyzing hyperspectral image. Obtain end-members (pure spectral signatures) present in hyperspectral image as output.

Analysis Steps Pre-processing: rank and end- members estimation (MOCA algorithm). Data Depletion (select data upon convex hull). Run MVT (apply linear programming) and concurrently perform constraints depletion. Get end-members and compare with MOCA end-members. Pre- processing Data depletion MVT MVT end- members MOCA end- members compare

Assumptions LMM – Linear Mixture Model. Every pixel is a linear combination of pure spectral signatures (end members). End members are linearly independent. Pixels-scatter-diagram is convex. Located in the first octant (for 3D).

MVT Variants Dark Point Fixed (DPFT) - dark point reliably known. - better when no bias. Fixed Point Free (FPFT) - dark point not known. - better when constant bias applied to data.

Pixels-Scatter-Diagram for 3-Bands Dist. Generally looks like a “tear drop”. P i represent the end members. Define facets of a minimum volume circumscribing simplex. O P3P3 P2P2 P1P1 dark point This facet is x+y+z=1 data

MVT Algorithm – DPFT DFPT selected – due to random bias applied by scanner. Create simplex without moving actual data. Project data onto u T x=1 Data Depletion Create start simplex Get constraints and deplete them Rotate k’th facet (linear programming – simplex method) k=k+1 k=1 End members If k=n+1 then k=1

Data Depletion Only data points upon the convex hull define a simplex. Choose these points by applying variant of Gram-Schmidt orthogonalization process. should leave 10% of total data.

Constraints Depletion Applied when data depletion process leaves too many points. Remove redundant constraints, which do not contribute to creation of feasible region (linear programming). Feasible region

Synthetic data results Blue circled – MOCA end-members Red points – after data depletion Azure – MVT end-members Arial view: - White noise applied - Constant bias applied

Real image results random bias Three images represent each end member

Discussion Creates a minimum volume simplex for a given data. Extremely efficient when bias is constant. Preserves rare-vectors – MOCA and MVT do not ignore abnormalities in an image. MVT is very sensitive to random bias. Sensitive to noise.