Random Thoughts 2012 (COMP 066) Jan-Michael Frahm Jared Heinly.

Slides:



Advertisements
Similar presentations
Modeling of Data. Basic Bayes theorem Bayes theorem relates the conditional probabilities of two events A, and B: A might be a hypothesis and B might.
Advertisements

Sampling: Final and Initial Sample Size Determination
776 Computer Vision Jared Heinly Spring 2014 (slides borrowed from Jan-Michael Frahm, Svetlana Lazebnik, and others)
© 2010 Pearson Prentice Hall. All rights reserved Least Squares Regression Models.
Fitting. We’ve learned how to detect edges, corners, blobs. Now what? We would like to form a higher-level, more compact representation of the features.
Point and Confidence Interval Estimation of a Population Proportion, p
Geometric Optimization Problems in Computer Vision.
The Basics of Regression continued
Triangulation and Multi-View Geometry Class 9 Read notes Section 3.3, , 5.1 (if interested, read Triggs’s paper on MVG using tensor notation, see.
Fitting. Choose a parametric object/some objects to represent a set of tokens Most interesting case is when criterion is not local –can’t tell whether.
Lecture 10: Robust fitting CS4670: Computer Vision Noah Snavely.
1Jana Kosecka, CS 223b EM and RANSAC EM and RANSAC.
Random Thoughts 2012 (COMP 066) Jan-Michael Frahm Jared Heinly.
Monté Carlo Simulation MGS 3100 – Chapter 9. Simulation Defined A computer-based model used to run experiments on a real system.  Typically done on a.
Introduction to ModelingMonte Carlo Simulation Expensive Not always practical Time consuming Impossible for all situations Can be complex Cons Pros Experience.
Hypothesis Testing and T-Tests. Hypothesis Tests Related to Differences Copyright © 2009 Pearson Education, Inc. Chapter Tests of Differences One.
Random Thoughts 2012 (COMP 066) Jan-Michael Frahm Jared Heinly source: fivethirtyeight.com.
Ewa Lukasik - Jakub Lawik - Juan Mojica - Xiaodong Xu.
More About Significance Tests
+ Chapter 9 Summary. + Section 9.1 Significance Tests: The Basics After this section, you should be able to… STATE correct hypotheses for a significance.
Advanced Computer Vision Feature-based Alignment Lecturer: Lu Yi & Prof. Fuh CSIE NTU.
Chapter 8: Confidence Intervals
Confidence Intervals (Chapter 8) Confidence Intervals for numerical data: –Standard deviation known –Standard deviation unknown Confidence Intervals for.
Random Thoughts 2012 (COMP 066) Jan-Michael Frahm Jared Heinly.
Basic Business Statistics, 10e © 2006 Prentice-Hall, Inc. Chap 8-1 Chapter 8 Confidence Interval Estimation Basic Business Statistics 11 th Edition.
Wiener Processes and Itô’s Lemma Chapter 12 1 Options, Futures, and Other Derivatives, 7th Edition, Copyright © John C. Hull 2008.
Chapter 14 Monte Carlo Simulation Introduction Find several parameters Parameter follow the specific probability distribution Generate parameter.
Chapter 13 Wiener Processes and Itô’s Lemma
PARAMETRIC STATISTICAL INFERENCE
1 Sampling Distributions Lecture 9. 2 Background  We want to learn about the feature of a population (parameter)  In many situations, it is impossible.
University of Ottawa - Bio 4118 – Applied Biostatistics © Antoine Morin and Scott Findlay 08/10/ :23 PM 1 Some basic statistical concepts, statistics.
AP Statistics Exam Review
10.1 Options, Futures, and Other Derivatives, 4th edition © 1999 by John C. Hull Model of the Behavior of Stock Prices Chapter 10.
Discrete Distributions The values generated for a random variable must be from a finite distinct set of individual values. For example, based on past observations,
Random Thoughts 2012 (COMP 066) Jan-Michael Frahm Jared Heinly.
Example: line fitting. n=2 Model fitting Measure distances.
Estimating a Population Proportion
1 SMU EMIS 7364 NTU TO-570-N Inferences About Process Quality Updated: 2/3/04 Statistical Quality Control Dr. Jerrell T. Stracener, SAE Fellow.
1 Chapter 19 Monte Carlo Valuation. 2 Simulation of future stock prices and using these simulated prices to compute the discounted expected payoff of.
Basic Numerical Procedures Chapter 19 1 Options, Futures, and Other Derivatives, 7th Edition, Copyright © John C. Hull 2008.
Simulation is the process of studying the behavior of a real system by using a model that replicates the behavior of the system under different scenarios.
Example: Bioassay experiment Problem statement –Observations: At each level of dose, 5 animals are tested, and number of death are observed.
CHEMISTRY ANALYTICAL CHEMISTRY Fall Lecture 6.
RANSAC Robust model estimation from data contaminated by outliers Ondřej Chum.
Random Thoughts 2012 (COMP 066) Jan-Michael Frahm Jared Heinly.
Monte-Carlo Simulations Seminar Project. Task  To Build an application in Excel/VBA to solve option prices.  Use a stochastic volatility in the model.
Inferring the Mean and Standard Deviation of a Population.
Sampling and estimation Petter Mostad
Business Statistics: A First Course (3rd Edition)
Chapter 19 Monte Carlo Valuation. Copyright © 2006 Pearson Addison-Wesley. All rights reserved Monte Carlo Valuation Simulation of future stock.
摹擬介紹: 問題求解: 確定及不確定 摹擬模式: 隨機及機遇. How did Monte Carlo simulation get its name? Monte Carlo simulation was named for Monte Carlo, Monaco, where the primary.
1 1 Slide Simulation Professor Ahmadi. 2 2 Slide Simulation Chapter Outline n Computer Simulation n Simulation Modeling n Random Variables and Pseudo-Random.
1 BA 555 Practical Business Analysis Linear Programming (LP) Sensitivity Analysis Simulation Agenda.
S TOCHASTIC M ODELS L ECTURE 4 P ART II B ROWNIAN M OTIONS Nan Chen MSc Program in Financial Engineering The Chinese University of Hong Kong (Shenzhen)
Simulation Chapter 16 of Quantitative Methods for Business, by Anderson, Sweeney and Williams Read sections 16.1, 16.2, 16.3, 16.4, and Appendix 16.1.
Robust Estimation Course web page: vision.cis.udel.edu/~cv April 23, 2003  Lecture 25.
Fitting.
Ka-fu Wong © 2007 ECON1003: Analysis of Economic Data Lesson0-1 Supplement 2: Comparing the two estimators of population variance by simulations.
Chapter 13 Wiener Processes and Itô’s Lemma 1. Stochastic Processes Describes the way in which a variable such as a stock price, exchange rate or interest.
Unit 3: Probability.  You will need to be able to describe how you will perform a simulation  Create a correspondence between random numbers and outcomes.
Computer Simulation Henry C. Co Technology and Operations Management,
Chapter 19 Monte Carlo Valuation.
Wiener Processes and Itô’s Lemma
Homography From Wikipedia In the field of computer vision, any
A special case of calibration
Lecture 2 – Monte Carlo method in finance
Chapter 14 Wiener Processes and Itô’s Lemma
Calibration and homographies
CS5760: Computer Vision Lecture 9: RANSAC Noah Snavely
CS5760: Computer Vision Lecture 9: RANSAC Noah Snavely
Presentation transcript:

Random Thoughts 2012 (COMP 066) Jan-Michael Frahm Jared Heinly

Last class t-distribution (Excel: T.DIST. ) if:  unknown standard deviation  if low number of samples 2

Last Class 1.For each pair take the first value minus the second value to get the paired difference 2.Calculate the mean difference and the standard deviation σ of all samples 3.Calculate the standard error of the sample 4.z-value 5.Determine the p-value 3

Last Class Random number generators (code for random number generator at  hardware generators produce truly random numbers but are slow  Pseudo random number generator is fast but not truly random which can be a problem with security applications Slot machine simulation (assignment for Monday) 4

What do Statistics Mean? How to we know how to interpret a poll of Obama 50%±3% and Romney 48%±3%? How do we interpret an average grows of 10% of the stock market? 5 Average depth 3ft

Monte Carlo Simulation Simulation allows us to imitate a real world situation to obtain an understanding of it Monte Carlo Simulation is one of the frequently used simulations Monte Carlo simulation was named for Monte Carlo, Monaco, where the primary attractions are casinos containing games of chance. Games of chance such as roulette wheels, dice, and slot machines, exhibit random behavior. Chance is how the simulation choses its variable values 6

Monte Carlo Simulation: Random Variables Random variables are used to model the uncertainties in the real-world Define range and distribution of the variable  Discrete  Bernoulli (success and failure)  Binomial distribution  Continous  uniform distribution  normal distribution  student distribution 7

Discrete Variables 8 1. A Bernoulli Random Variable: generate a single random variable between (0,1) Baby Boy Girl 1/2 IF ( RAND( ) <1/2, ‘ boy ’, ’ girl ’ ) 2. A Binomial Random Variable with n trials: BINOMINV(RAND(.),n,p)

Continuous Distributions Uniform distribution  RAND() Normal distribution  NORMSINV(RAND()) STUDENT (T) distribution  TINV(RAND(),degrees of freedom) 9

Simulation For simulation evaluate the problem for many different values of the random variables The results of the simulation can then be analyzed to obtain summary statistics  mean  variance  medium …… 10

Polls How can we simulate: “a poll of Obama 50%±3% and Romney 48%±3%?” 11

Polls the mean value of the poll for Obama is 50% the standard deviation is?  with 95% confidence level z*=1.96  this mean that for the z-distribution 3% are within 1.96 standard deviations.  hence standard deviation is 1.53%=3%/1.96 the mean value of the poll for Romney is 48% standard deviation is also 1.53% 12

Vote Distributions Hence the possible votes are distributed in the following manner 13

Simulate voting To simulate the voting we can now draw random samples from the vote distribution of the candidates  random number generator with standard normal distribution  scale the value by the standard deviation  shift to mean value of the desired distribution (50% Obama, 48% Romney) 14

Stock Market How do we interpret an average grows of 10% of the stock market? Again the average grows of 10% only applies for long periods of time Stock market is often described by Brownian motion  the presumably random moving of particles suspended in a fluid  random motion driven by random events 15

Model for Stock Market Drift annually is 10%, which is the average increase in value The standard deviation is called volatility and it is 405 annually Often expressed in daily values:  drift daily = % (assuming 252 trading days)  volatility daily = 2.52% 16

Model for Stock Market The daily value S t behaves in the following way:  μ is daily drift  σ is valatility  T is time between the t and t-1 Simplified version 17

Simulation Simulate by using random variable z t to predict daily stock price 18

Using Randomness to Estimate Models Estimating models from measurement data  line fitting  finding a model to explain the data Least squares fitting  sensitive to outliers Using Randomness to find the correct model 19

Robust data selection: RANSAC Estimation of line from point data Select m samples Compute n-parameter solution Evaluate on {potential line points} Best solution so far? Keep it {potential line points} yesno good solution probability >0.99 no Best solution, {inlier}, {outlier} {inlier samples }

How many iterations are needed? We want to be sure to have a good line with 99% probability  depends on ratio ε of good points to bad points  depends on size s of sample  depends on number of iterations i What is the probability of a good sample? es es What is the probability of no good sample in i iterations? (1-e s ) i So probability of good solution is 1-(1-e s ) i 21

Camera Motion Estimation Where where the cameras upon photo taking? 22

3D from images Camera 1 Camera 2 Camera 3

24 Epipolar geometry estimation Typically done with RANSAC [RANSAC Fishler & Bolles ‘81] Camera motion can be described through 3x3 matrix F (Step 1) Extract features (Step 2) Set of potential correspondences (Step 3) do (Step 3.1) select minimal sample (i.e. 7 matches) (Step 3.2) compute solution(s) for F (Step 3.3) count inliers, if not promising stop until  (#inliers,#samples)<95% #inliers90%80%70%50%10% #samples ~30 million (generate hypothesis) (verify hypothesis) [Raguram, Frahm, Pollefeys, ECCV’08] [Raguram, Frahm, Pollefeys, ICCV’09]

Reading Assignment for Monday Moldinov Chapter 9 25