Stanford CS223B Computer Vision, Winter 2006 Lecture 6 Stereo II Professor Sebastian Thrun CAs: Dan Maynes-Aminzade, Mitul Saha, Greg Corrado Stereo.

Slides:



Advertisements
Similar presentations
Stereo Vision Reading: Chapter 11
Advertisements

CS 376b Introduction to Computer Vision 04 / 21 / 2008 Instructor: Michael Eckmann.
Gratuitous Picture US Naval Artillery Rangefinder from World War I (1918)!!
Stereo Many slides adapted from Steve Seitz. Binocular stereo Given a calibrated binocular stereo pair, fuse it to produce a depth image Where does the.
MASKS © 2004 Invitation to 3D vision Lecture 7 Step-by-Step Model Buidling.
Lecture 8: Stereo.
Stereo.
Active Contours / Planes Sebastian Thrun, Gary Bradski, Daniel Russakoff Stanford CS223B Computer Vision Some slides.
Last Time Pinhole camera model, projection
Stanford CS223B Computer Vision, Winter 2005 Lecture 5: Stereo I Sebastian Thrun, Stanford Rick Szeliski, Microsoft Hendrik Dahlkamp and Dan Morris, Stanford.
Stanford CS223B Computer Vision, Winter 2005 Lecture 6: Stereo 2 Sebastian Thrun, Stanford Rick Szeliski, Microsoft Hendrik Dahlkamp and Dan Morris, Stanford.
Stanford CS223B Computer Vision, Winter 2007 Lecture 6 Advanced Stereo Professors Sebastian Thrun and Jana Košecká CAs: Vaibhav Vaish and David Stavens.
Multiple View Geometry : Computational Photography Alexei Efros, CMU, Fall 2005 © Martin Quinn …with a lot of slides stolen from Steve Seitz and.
© 2004 by Davi GeigerComputer Vision April 2004 L1.1 Binocular Stereo Left Image Right Image.
Computer Vision : CISC 4/689 Adaptation from: Prof. James M. Rehg, G.Tech.
Stanford CS223B Computer Vision, Winter 2006 Lecture 5 Stereo I
Stereo Matching Vision for Graphics CSE 590SS, Winter 2001 Richard Szeliski.
Stanford CS223B Computer Vision, Winter 2006 Lecture 8 Structure From Motion Professor Sebastian Thrun CAs: Dan Maynes-Aminzade, Mitul Saha, Greg Corrado.
Stereopsis Mark Twain at Pool Table", no date, UCR Museum of Photography.
The plan for today Camera matrix
CS 223b 1 More on stereo and correspondence. CS 223b 2 =?f g Mostpopular For each window, match to closest window on epipolar line in other image. (slides.
Stereo Computation using Iterative Graph-Cuts
Lecture 11: Stereo and optical flow CS6670: Computer Vision Noah Snavely.
3D Computer Vision and Video Computing 3D Vision Lecture 15 Stereo Vision (II) CSC 59866CD Fall 2004 Zhigang Zhu, NAC 8/203A
Stanford CS223B Computer Vision, Winter 2006 Lecture 11 Filters / Motion Tracking Professor Sebastian Thrun CAs: Dan Maynes-Aminzade, Mitul Saha, Greg.
1 Stanford CS223B Computer Vision, Winter 2006 Lecture 7 Optical Flow Professor Sebastian Thrun CAs: Dan Maynes-Aminzade, Mitul Saha, Greg Corrado Slides.
May 2004Stereo1 Introduction to Computer Vision CS / ECE 181B Tuesday, May 11, 2004  Multiple view geometry and stereo  Handout #6 available (check with.
CSE473/573 – Stereo Correspondence
Announcements PS3 Due Thursday PS4 Available today, due 4/17. Quiz 2 4/24.
Stereo Sebastian Thrun, Gary Bradski, Daniel Russakoff Stanford CS223B Computer Vision (with slides by James Rehg and.
Multiple View Geometry : Computational Photography Alexei Efros, CMU, Fall 2006 © Martin Quinn …with a lot of slides stolen from Steve Seitz and.
Stereo matching “Stereo matching” is the correspondence problem –For a point in Image #1, where is the corresponding point in Image #2? C1C1 C2C2 ? ? C1C1.
Stereo matching Class 10 Read Chapter 7 Tsukuba dataset.
3-D Scene u u’u’ Study the mathematical relations between corresponding image points. “Corresponding” means originated from the same 3D point. Objective.
Sebastian Thrun CS223B Computer Vision, Winter Stanford CS223B Computer Vision, Winter 2006 Lecture 4 Camera Calibration Professor Sebastian Thrun.
Lecture 11 Stereo Reconstruction I Lecture 11 Stereo Reconstruction I Mata kuliah: T Computer Vision Tahun: 2010.
Structure from images. Calibration Review: Pinhole Camera.
What we didn’t have time for CS664 Lecture 26 Thursday 12/02/04 Some slides c/o Dan Huttenlocher, Stefano Soatto, Sebastian Thrun.
Lecture 12 Stereo Reconstruction II Lecture 12 Stereo Reconstruction II Mata kuliah: T Computer Vision Tahun: 2010.
Recap from Monday Image Warping – Coordinate transforms – Linear transforms expressed in matrix form – Inverse transforms useful when synthesizing images.
Stereo Vision Reading: Chapter 11 Stereo matching computes depth from two or more images Subproblems: –Calibrating camera positions. –Finding all corresponding.
Stereo Dan Kong.
CS654: Digital Image Analysis Lecture 8: Stereo Imaging.
Geometry 3: Stereo Reconstruction Introduction to Computer Vision Ronen Basri Weizmann Institute of Science.
Stereo Many slides adapted from Steve Seitz.
#? rahul swaminathan (T-Labs) & professor patrick baudisch hci2 hasso-plattner institute determining depth.
Stereo Many slides adapted from Steve Seitz. Binocular stereo Given a calibrated binocular stereo pair, fuse it to produce a depth image image 1image.
Computer Vision, Robert Pless
Lec 22: Stereo CS4670 / 5670: Computer Vision Kavita Bala.
MACHINE LEARNING 8. Clustering. Motivation Based on E ALPAYDIN 2004 Introduction to Machine Learning © The MIT Press (V1.1) 2  Classification problem:
Computer Vision Stereo Vision. Bahadir K. Gunturk2 Pinhole Camera.
Computer Vision Lecture #10 Hossam Abdelmunim 1 & Aly A. Farag 2 1 Computer & Systems Engineering Department, Ain Shams University, Cairo, Egypt 2 Electerical.
CSE 185 Introduction to Computer Vision Stereo. Taken at the same time or sequential in time stereo vision structure from motion optical flow Multiple.
Bahadir K. Gunturk1 Phase Correlation Bahadir K. Gunturk2 Phase Correlation Take cross correlation Take inverse Fourier transform  Location of the impulse.
Lecture 16: Stereo CS4670 / 5670: Computer Vision Noah Snavely Single image stereogram, by Niklas EenNiklas Een.
stereo Outline : Remind class of 3d geometry Introduction
Jochen Triesch, UC San Diego, 1 Stereo Outline: parallel camera axes convergent axes, epipolar geometry correspondence.
Solving for Stereo Correspondence Many slides drawn from Lana Lazebnik, UIUC.
Correspondence and Stereopsis Original notes by W. Correa. Figures from [Forsyth & Ponce] and [Trucco & Verri]
John Morris Stereo Vision (continued) Iolanthe returns to the Waitemata Harbour.
Advanced Computer Vision Chapter 11 Stereo Correspondence Presented by: 蘇唯誠 指導教授 : 傅楸善 博士.
Stereo Matching Using Dynamic Programming
數位三維視訊 楊 家 輝 Jar-Ferr Yang 電腦與通信工程研究所 電機工程學系 國立成功大學 Institute of Computer and Communication Engineering Department of Electrical Engineering National Cheng.
Correspondence and Stereopsis. Introduction Disparity – Informally: difference between two pictures – Allows us to gain a strong sense of depth Stereopsis.
CSE 185 Introduction to Computer Vision Stereo 2.
Stereo CS4670 / 5670: Computer Vision Noah Snavely Single image stereogram, by Niklas EenNiklas Een.
Geometry 3: Stereo Reconstruction
EECS 274 Computer Vision Stereopsis.
Computer Vision Stereo Vision.
Stereo vision Many slides adapted from Steve Seitz.
Presentation transcript:

Stanford CS223B Computer Vision, Winter 2006 Lecture 6 Stereo II Professor Sebastian Thrun CAs: Dan Maynes-Aminzade, Mitul Saha, Greg Corrado Stereo

Sebastian Thrun Stanford University CS223B Computer Vision Stereo Vision: Outline n Basic Equations n Epipolar Geometry n Image Rectification n Reconstruction n Correspondence n Active Range Imaging Technology n Dense and Layered Stereo n Smoothing With Markov Random Fields

Sebastian Thrun Stanford University CS223B Computer Vision A Last Word on Preprocessing….

Sebastian Thrun Stanford University CS223B Computer Vision Epipolar Rectified Images Epipolar line

Sebastian Thrun Stanford University CS223B Computer Vision Epipolar Rectified Images Source: A. Fusiello, Verona, 2000]

Sebastian Thrun Stanford University CS223B Computer Vision Image Normalization n Even when the cameras are identical models, there can be differences in gain and sensitivity. n The cameras do not see exactly the same surfaces, so their overall light levels can differ. n For these reasons and more, it is a good idea to normalize the pixels in each window:

Sebastian Thrun Stanford University CS223B Computer Vision Stereo Vision: Outline n Basic Equations n Epipolar Geometry n Image Rectification n Reconstruction n Correspondence n Active Range Imaging Technology n Dense and Layered Stereo n Smoothing With Markov Random Fields

Sebastian Thrun Stanford University CS223B Computer Vision Correspondence Phantom points

Sebastian Thrun Stanford University CS223B Computer Vision Correspondence via Correlation Rectified images LeftRight scanline SSD error disparity (Same as max-correlation / max-cosine for normalized image patch)

Sebastian Thrun Stanford University CS223B Computer Vision Images as Vectors LeftRight Each window is a vector in an m 2 dimensional vector space. Normalization makes them unit length.

Sebastian Thrun Stanford University CS223B Computer Vision Image Metrics (Normalized) Sum of Squared Differences Normalized Correlation

Sebastian Thrun Stanford University CS223B Computer Vision Correspondence Using Correlation LeftDisparity Map Images courtesy of Point Grey Research

Sebastian Thrun Stanford University CS223B Computer Vision LEFT IMAGE corner line structure Correspondence By Features

Sebastian Thrun Stanford University CS223B Computer Vision Correspondence By Features RIGHT IMAGE corner line structure n Search in the right image… the disparity (dx, dy) is the displacement when the similarity measure is maximum

Sebastian Thrun Stanford University CS223B Computer Vision Stereo Correspondences …… Left scanlineRight scanline

Sebastian Thrun Stanford University CS223B Computer Vision Stereo Correspondences …… Left scanlineRight scanline Match OcclusionDisocclusion

Sebastian Thrun Stanford University CS223B Computer Vision Search Over Correspondences Three cases: –Sequential – cost of match –Occluded – cost of no match –Disoccluded – cost of no match Left scanline Right scanline Occluded Pixels Disoccluded Pixels

Sebastian Thrun Stanford University CS223B Computer Vision Scan across grid computing optimal cost for each node given its upper-left neighbors. Backtrack from the terminal to get the optimal path. Occluded Pixels Left scanline Dis-occluded Pixels Right scanline Terminal Stereo Matching with Dynamic Programming

Sebastian Thrun Stanford University CS223B Computer Vision Stereo Matching with Dynamic Programming Dynamic programming yields the optimal path through grid. This is the best set of matches that satisfy the ordering constraint Occluded Pixels Left scanline Dis-occluded Pixels Right scanline Start End

Sebastian Thrun Stanford University CS223B Computer Vision Scan across grid computing optimal cost for each node given its upper-left neighbors. Backtrack from the terminal to get the optimal path. Occluded Pixels Left scanline Dis-occluded Pixels Right scanline Terminal Stereo Matching with Dynamic Programming

Sebastian Thrun Stanford University CS223B Computer Vision Scan across grid computing optimal cost for each node given its upper-left neighbors. Backtrack from the terminal to get the optimal path. Occluded Pixels Left scanline Dis-occluded Pixels Right scanline Terminal Stereo Matching with Dynamic Programming

Sebastian Thrun Stanford University CS223B Computer Vision Dense Stereo Matching: Examples n View extrapolation results input depth image novel view [Matthies,Szeliski,Kanade’88]

Sebastian Thrun Stanford University CS223B Computer Vision Dense Stereo Matching n Some other view extrapolation results inputdepth imagenovel view

Sebastian Thrun Stanford University CS223B Computer Vision Dense Stereo Matching n Compute certainty map from correlations input depth map certainty map

Sebastian Thrun Stanford University CS223B Computer Vision DP for Correspondence n Does this always work? n When would it fail? –Failure Example 1 –Failure Example 2 –Failure Example 3

Sebastian Thrun Stanford University CS223B Computer Vision Correspondence Problem 1 n It is fundamentally ambiguous, even with stereo constraints Ordering constraint……and its failure Figure from Forsyth & Ponce

Sebastian Thrun Stanford University CS223B Computer Vision Correspondence Problem 2 n Correspondence fail for smooth surfaces n There is currently no good solution to the correspondence problem

Sebastian Thrun Stanford University CS223B Computer Vision Correspondence Problem 3 n Regions without texture n Highly Specular surfaces n Translucent objects

Sebastian Thrun Stanford University CS223B Computer Vision Stereo Vision: Outline n Basic Equations n Epipolar Geometry n Image Rectification n Reconstruction n Correspondence n Active Range Imaging Technology n Dense and Layered Stereo n Smoothing With Markov Random Fields

Sebastian Thrun Stanford University CS223B Computer Vision How can We Improve Stereo? Space-time stereo scanner uses unstructured light to aid in correspondence Result: Dense 3D mesh (noisy)

Sebastian Thrun Stanford University CS223B Computer Vision Prof Marc Stanford By James Davis, Honda Research, Now UCSC

Sebastian Thrun Stanford University CS223B Computer Vision rectified Active Stereo (Structured Light)

Sebastian Thrun Stanford University CS223B Computer Vision Structured Light: 3-D Result 3D Model3D Snapshot By James Davis, Honda Research

Sebastian Thrun Stanford University CS223B Computer Vision Time of Flight Sensor: Shutter

Sebastian Thrun Stanford University CS223B Computer Vision Time of Flight Sensor: Shutter

Sebastian Thrun Stanford University CS223B Computer Vision Time of Flight Sensor: Shutter

Sebastian Thrun Stanford University CS223B Computer Vision Stereo Vision: Outline n Basic Equations n Epipolar Geometry n Image Rectification n Reconstruction n Correspondence n Active Range Imaging Technology n Layered Stereo n Smoothing With Markov Random Fields

Sebastian Thrun Stanford University CS223B Computer Vision Disclaimer n The Following Material Shall Not Be Required For the Midterm Exam

Sebastian Thrun Stanford University CS223B Computer Vision Layered Stereo n Assign pixel to different “layers” (objects, sprites)

Sebastian Thrun Stanford University CS223B Computer Vision Layered Stereo n Track each layer from frame to frame, compute plane eqn. and composite mosaic n Re-compute pixel assignment by comparing original images to sprites

Sebastian Thrun Stanford University CS223B Computer Vision Layered Stereo n Re-synthesize original or novel images from collection of sprites

Sebastian Thrun Stanford University CS223B Computer Vision Layered Stereo n Advantages: –can represent occluded regions –can represent transparent and border (mixed) pixels (sprites have alpha value per pixel) –works on texture-less interior regions n Limitations: –fails for high depth-complexity scenes

Sebastian Thrun Stanford University CS223B Computer Vision Fitting Planar Surfaces (with EM) ** ****

Sebastian Thrun Stanford University CS223B Computer Vision Expectation Maximization n 3D Model: Planar surface in 3D Distance point-surface surface normal  y x z displacement 

Sebastian Thrun Stanford University CS223B Computer Vision Mixture Measurement Model Case 1: Measurement z i caused by plane  j  Case 2: Measurement z i caused by something else

Sebastian Thrun Stanford University CS223B Computer Vision Measurement Model with Correspondences correspondence variables C : }

Sebastian Thrun Stanford University CS223B Computer Vision Expected Log-Likelihood Function …after some simple math mapping with known data association probabilistic data association

Sebastian Thrun Stanford University CS223B Computer Vision The EM Algorithm n E-step: given plane params, compute n M-step: given expectations, compute

Sebastian Thrun Stanford University CS223B Computer Vision Choosing the “Right” Number of Planes: AIC J=2J=3J=5J=0J=1J=4 increased data likelihoodincreased prior probability

Sebastian Thrun Stanford University CS223B Computer Vision Determining Number of Surfaces J =1 First model component * * J =1 E-Step * * J =3 Add model components J =3 E-Step J =3 M-step J =1 Prune model J =3 Add model components J =3 E/M Steps * J =2 Prune model

Sebastian Thrun Stanford University CS223B Computer Vision Layered Stereo n Resulting sprite collection

Sebastian Thrun Stanford University CS223B Computer Vision Layered Stereo n Estimated depth map

Sebastian Thrun Stanford University CS223B Computer Vision Stereo Vision: Outline n Basic Equations n Epipolar Geometry n Image Rectification n Reconstruction n Correspondence n Active Range Imaging Technology n Dense and Layered Stereo n Smoothing With Markov Random Fields

Sebastian Thrun Stanford University CS223B Computer Vision Motivation and Goals James Diebel

Sebastian Thrun Stanford University CS223B Computer Vision Motivation and Goals James Diebel

Sebastian Thrun Stanford University CS223B Computer Vision Network of Constraints (Markov Random Field) James Diebel

Sebastian Thrun Stanford University CS223B Computer Vision MRF Approach to Smoothing n Potential function: contains a sensor-model term and a surface prior n The edge potential is important! n Minimize  by conjugate gradient –Optimize systems with tens of thousands of parameters in just a couple seconds –Time to converge is O(N), between 0.7 sec (25,000 nodes in the MRF) and 25 sec (900,000 nodes) Diebel/Thrun, 2006

Sebastian Thrun Stanford University CS223B Computer Vision Possible Edge Potential Functions

Sebastian Thrun Stanford University CS223B Computer Vision Results: Smoothing James Diebel

Sebastian Thrun Stanford University CS223B Computer Vision Results: Smoothing James Diebel

Sebastian Thrun Stanford University CS223B Computer Vision Results: Smoothing James Diebel

Sebastian Thrun Stanford University CS223B Computer Vision Results: Smoothing James Diebel

Sebastian Thrun Stanford University CS223B Computer Vision Movies… Movies in Windows Media Player

Sebastian Thrun Stanford University CS223B Computer Vision Stereo Vision: Outline n Basic Equations n Epipolar Geometry n Image Rectification n Reconstruction n Correspondence n Active Range Imaging Technology n Dense and Layered Stereo n Smoothing With Markov Random Fields