Stereo and Structure from Motion

Slides:



Advertisements
Similar presentations
Lecture 11: Two-view geometry
Advertisements

Stereo Vision Reading: Chapter 11
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.
Stereo and Projective Structure from Motion
Recap from Previous Lecture Tone Mapping – Preserve local contrast or detail at the expense of large scale contrast. – Changing the brightness within.
Lecture 8: Stereo.
Stereo.
776 Computer Vision Jan-Michael Frahm, Enrique Dunn Spring 2012.
Camera calibration and epipolar geometry
Structure from motion.
Last Time Pinhole camera model, projection
CS6670: Computer Vision Noah Snavely Lecture 17: Stereo
Multiple View Geometry : Computational Photography Alexei Efros, CMU, Fall 2005 © Martin Quinn …with a lot of slides stolen from Steve Seitz and.
Epipolar geometry. (i)Correspondence geometry: Given an image point x in the first view, how does this constrain the position of the corresponding point.
Structure from motion. Multiple-view geometry questions Scene geometry (structure): Given 2D point matches in two or more images, where are the corresponding.
Lecture 21: Multiple-view geometry and structure from motion
Stereopsis Mark Twain at Pool Table", no date, UCR Museum of Photography.
The plan for today Camera matrix
3D from multiple views : Rendering and Image Processing Alexei Efros …with a lot of slides stolen from Steve Seitz and Jianbo Shi.
Lecture 20: Two-view geometry CS6670: Computer Vision Noah Snavely.
Lec 21: Fundamental Matrix
CSE473/573 – Stereo Correspondence
Announcements PS3 Due Thursday PS4 Available today, due 4/17. Quiz 2 4/24.
Stereo Guest Lecture by Li Zhang
Project 1 artifact winners Project 2 questions Project 2 extra signup slots –Can take a second slot if you’d like Announcements.
Multiple View Geometry : Computational Photography Alexei Efros, CMU, Fall 2006 © Martin Quinn …with a lot of slides stolen from Steve Seitz and.
3-D Scene u u’u’ Study the mathematical relations between corresponding image points. “Corresponding” means originated from the same 3D point. Objective.
Epipolar Geometry and Stereo Vision Computer Vision CS 543 / ECE 549 University of Illinois Derek Hoiem 04/12/11 Many slides adapted from Lana Lazebnik,
9 – Stereo Reconstruction
Multi-view geometry. Multi-view geometry problems Structure: Given projections of the same 3D point in two or more images, compute the 3D coordinates.
Computer Vision Spring ,-685 Instructor: S. Narasimhan WH 5409 T-R 10:30am – 11:50am Lecture #15.
Epipolar Geometry and Stereo Vision Computer Vision CS 543 / ECE 549 University of Illinois Derek Hoiem 03/05/15 Many slides adapted from Lana Lazebnik,
Camera Calibration & Stereo Reconstruction Jinxiang Chai.
Structure from images. Calibration Review: Pinhole Camera.
Multi-view geometry.
Lecture 12 Stereo Reconstruction II Lecture 12 Stereo Reconstruction II Mata kuliah: T Computer Vision Tahun: 2010.
Structure from Motion Computer Vision CS 143, Brown James Hays 11/18/11 Many slides adapted from Derek Hoiem, Lana Lazebnik, Silvio Saverese, Steve Seitz,
Recap from Monday Image Warping – Coordinate transforms – Linear transforms expressed in matrix form – Inverse transforms useful when synthesizing images.
Epipolar geometry Epipolar Plane Baseline Epipoles Epipolar Lines
Stereo Vision Reading: Chapter 11 Stereo matching computes depth from two or more images Subproblems: –Calibrating camera positions. –Finding all corresponding.
Stereo Readings Szeliski, Chapter 11 (through 11.5) Single image stereogram, by Niklas EenNiklas Een.
Stereo Many slides adapted from Steve Seitz.
Project 2 code & artifact due Friday Midterm out tomorrow (check your ), due next Fri Announcements TexPoint fonts used in EMF. Read the TexPoint.
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.
Announcements Project 3 due Thursday by 11:59pm Demos on Friday; signup on CMS Prelim to be distributed in class Friday, due Wednesday by the beginning.
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
Feature Matching. Feature Space Outlier Rejection.
776 Computer Vision Jan-Michael Frahm Spring 2012.
Solving for Stereo Correspondence Many slides drawn from Lana Lazebnik, UIUC.
776 Computer Vision Jan-Michael Frahm & Enrique Dunn Spring 2013.
Project 2 due today Project 3 out today Announcements TexPoint fonts used in EMF. Read the TexPoint manual before you delete this box.: AAAAA.
Project 3 code & artifact due Tuesday Final project proposals due noon Wed (by ) –One-page writeup (from project web page), specifying: »Your team.
Multiple View Geometry and Stereo. Overview Single camera geometry – Recap of Homogenous coordinates – Perspective projection model – Camera calibration.
Introduction à la vision artificielle VIII Jean Ponce Web:
CSE 185 Introduction to Computer Vision Stereo 2.
Stereo CS4670 / 5670: Computer Vision Noah Snavely Single image stereogram, by Niklas EenNiklas Een.
Noah Snavely, Zhengqi Li
Epipolar Geometry and Stereo Vision
제 5 장 스테레오.
Stereo CSE 455 Linda Shapiro.
CS4670 / 5670: Computer Vision Kavita Bala Lec 27: Stereo.
Stereo and Structure from Motion
Epipolar geometry.
Stereo vision Many slides adapted from Steve Seitz.
Presentation transcript:

Stereo and Structure from Motion CS143, Brown James Hays Many slides by Kristen Grauman, Robert Collins, Derek Hoiem, Alyosha Efros, and Svetlana Lazebnik CS 376 Lecture 16: Stereo 1

Depth from disparity X z x x’ f f baseline C C’ (X – X’) / f = baseline / z X – X’ = (baseline*f) / z z = (baseline*f) / (X – X’) z x’ f baseline C’

Outline Human stereopsis Stereograms Epipolar geometry and the epipolar constraint Case example with parallel optical axes General case with calibrated cameras

General case, with calibrated cameras The two cameras need not have parallel optical axes. Vs. CS 376 Lecture 16: Stereo 1

Stereo correspondence constraints Given p in left image, where can corresponding point p’ be? CS 376 Lecture 16: Stereo 1

Stereo correspondence constraints CS 376 Lecture 16: Stereo 1

Epipolar constraint Geometry of two views constrains where the corresponding pixel for some image point in the first view must occur in the second view. It must be on the line carved out by a plane connecting the world point and optical centers. CS 376 Lecture 16: Stereo 1 9

Epipolar geometry Epipolar Line Epipolar Plane Epipole Baseline http://www.ai.sri.com/~luong/research/Meta3DViewer/EpipolarGeo.html CS 376 Lecture 16: Stereo 1 10

Epipolar geometry: terms Baseline: line joining the camera centers Epipole: point of intersection of baseline with image plane Epipolar plane: plane containing baseline and world point Epipolar line: intersection of epipolar plane with the image plane All epipolar lines intersect at the epipole An epipolar plane intersects the left and right image planes in epipolar lines Why is the epipolar constraint useful? CS 376 Lecture 16: Stereo 1

Epipolar constraint This is useful because it reduces the correspondence problem to a 1D search along an epipolar line. Image from Andrew Zisserman

Example CS 376 Lecture 16: Stereo 1

What do the epipolar lines look like? 1. Ol Or 2. Ol Or CS 376 Lecture 16: Stereo 1

Example: converging cameras Figure from Hartley & Zisserman CS 376 Lecture 16: Stereo 1 15

Example: parallel cameras Where are the epipoles? Figure from Hartley & Zisserman CS 376 Lecture 16: Stereo 1 16

Example: Forward motion What would the epipolar lines look like if the camera moves directly forward?

Example: Forward motion Epipole has same coordinates in both images. Points move along lines radiating from e: “Focus of expansion”

Fundamental matrix Let p be a point in left image, p’ in right image Epipolar relation p maps to epipolar line l’ p’ maps to epipolar line l Epipolar mapping described by a 3x3 matrix F It follows that l’ l p p’

Fundamental matrix This matrix F is called the “Essential Matrix” when image intrinsic parameters are known the “Fundamental Matrix” more generally (uncalibrated case) Can solve for F from point correspondences Each (p, p’) pair gives one linear equation in entries of F F has 9 entries, but really only 7 or 8 degrees of freedom. With 8 points it is simple to solve for F, but it is also possible with 7. See Marc Pollefey’s notes for a nice tutorial

Stereo image rectification

Stereo image rectification Reproject image planes onto a common plane parallel to the line between camera centers Pixel motion is horizontal after this transformation Two homographies (3x3 transform), one for each input image reprojection C. Loop and Z. Zhang. Computing Rectifying Homographies for Stereo Vision. IEEE Conf. Computer Vision and Pattern Recognition, 1999.

Rectification example

The correspondence problem Epipolar geometry constrains our search, but we still have a difficult correspondence problem.

Basic stereo matching algorithm If necessary, rectify the two stereo images to transform epipolar lines into scanlines For each pixel x in the first image Find corresponding epipolar scanline in the right image Examine all pixels on the scanline and pick the best match x’ Compute disparity x-x’ and set depth(x) = fB/(x-x’)

Correspondence search Left Right scanline Matching cost disparity Slide a window along the right scanline and compare contents of that window with the reference window in the left image Matching cost: SSD or normalized correlation

Correspondence search Left Right scanline SSD

Correspondence search Left Right scanline Norm. corr

Effect of window size Smaller window Larger window + More detail More noise Larger window + Smoother disparity maps Less detail smaller window: more detail, more noise bigger window: less noise, more detail

Failures of correspondence search Occlusions, repetition Textureless surfaces Non-Lambertian surfaces, specularities

Results with window search Data Window-based matching Ground truth

How can we improve window-based matching? So far, matches are independent for each point What constraints or priors can we add?

Stereo constraints/priors Uniqueness For any point in one image, there should be at most one matching point in the other image

Stereo constraints/priors Uniqueness For any point in one image, there should be at most one matching point in the other image Ordering Corresponding points should be in the same order in both views

Stereo constraints/priors Uniqueness For any point in one image, there should be at most one matching point in the other image Ordering Corresponding points should be in the same order in both views Ordering constraint doesn’t hold

Priors and constraints Uniqueness For any point in one image, there should be at most one matching point in the other image Ordering Corresponding points should be in the same order in both views Smoothness We expect disparity values to change slowly (for the most part)

Scanline stereo Try to coherently match pixels on the entire scanline Different scanlines are still optimized independently Left image Right image

“Shortest paths” for scan-line stereo Left image Right image Right occlusion s q Left occlusion t p correspondence Can be implemented with dynamic programming Ohta & Kanade ’85, Cox et al. ‘96 Slide credit: Y. Boykov

Coherent stereo on 2D grid Scanline stereo generates streaking artifacts Can’t use dynamic programming to find spatially coherent disparities/ correspondences on a 2D grid

Stereo matching as energy minimization (random field interpretation) W1(i ) W2(i+D(i )) D(i ) data term smoothness term Energy functions of this form can be minimized using graph cuts Y. Boykov, O. Veksler, and R. Zabih, Fast Approximate Energy Minimization via Graph Cuts, PAMI 2001

Many of these constraints can be encoded in an energy function and solved using graph cuts Before Graph cuts Ground truth Y. Boykov, O. Veksler, and R. Zabih, Fast Approximate Energy Minimization via Graph Cuts, PAMI 2001 For the latest and greatest: http://www.middlebury.edu/stereo/

Active stereo with structured light Project “structured” light patterns onto the object Simplifies the correspondence problem Allows us to use only one camera camera projector L. Zhang, B. Curless, and S. M. Seitz. Rapid Shape Acquisition Using Color Structured Light and Multi-pass Dynamic Programming. 3DPVT 2002

Kinect: Structured infrared light http://bbzippo.wordpress.com/2010/11/28/kinect-in-infrared/

Summary: Key idea: Epipolar constraint X X X x x’ x’ x’ Potential matches for x have to lie on the corresponding line l’. Potential matches for x’ have to lie on the corresponding line l.

Summary Epipolar geometry Stereo depth estimation Epipoles are intersection of baseline with image planes Matching point in second image is on a line passing through its epipole Fundamental matrix maps from a point in one image to a line (its epipolar line) in the other Can solve for F given corresponding points (e.g., interest points) Stereo depth estimation Estimate disparity by finding corresponding points along scanlines Depth is inverse to disparity

Slide credit: Noah Snavely Structure from motion Given a set of corresponding points in two or more images, compute the camera parameters and the 3D point coordinates ? Structure from motion solves the following problem: Given a set of images of a static scene with 2D points in correspondence, shown here as color-coded points, find… a set of 3D points P and a rotation R and position t of the cameras that explain the observed correspondences. In other words, when we project a point into any of the cameras, the reprojection error between the projected and observed 2D points is low. This problem can be formulated as an optimization problem where we want to find the rotations R, positions t, and 3D point locations P that minimize sum of squared reprojection errors f. This is a non-linear least squares problem and can be solved with algorithms such as Levenberg-Marquart. However, because the problem is non-linear, it can be susceptible to local minima. Therefore, it’s important to initialize the parameters of the system carefully. In addition, we need to be able to deal with erroneous correspondences. ? Camera 1 ? Camera 3 Camera 2 ? R1,t1 R3,t3 R2,t2 Slide credit: Noah Snavely

Structure from motion ambiguity If we scale the entire scene by some factor k and, at the same time, scale the camera matrices by the factor of 1/k, the projections of the scene points in the image remain exactly the same: It is impossible to recover the absolute scale of the scene!

How do we know the scale of image content?

Phil Tippett and Jon Berg stop-motion animate a shot with all three walkers (the background walkers are cutouts). Originally the plan had been to photograph the walkers against four-by-five Ektachrome transparencies shot in Norway; when these didn’t work as planned, matte artist Mike Pangrazio copied select Ektachromes onto large scenic backings.

Structure from motion ambiguity If we scale the entire scene by some factor k and, at the same time, scale the camera matrices by the factor of 1/k, the projections of the scene points in the image remain exactly the same More generally: if we transform the scene using a transformation Q and apply the inverse transformation to the camera matrices, then the images do not change

Projective structure from motion Given: m images of n fixed 3D points xij = Pi Xj , i = 1,… , m, j = 1, … , n Problem: estimate m projection matrices Pi and n 3D points Xj from the mn corresponding points xij x1j x2j x3j Xj P1 P2 P3 Slides from Lana Lazebnik

Projective structure from motion Given: m images of n fixed 3D points xij = Pi Xj , i = 1,… , m, j = 1, … , n Problem: estimate m projection matrices Pi and n 3D points Xj from the mn corresponding points xij With no calibration info, cameras and points can only be recovered up to a 4x4 projective transformation Q: X → QX, P → PQ-1 We can solve for structure and motion when 2mn >= 11m +3n – 15 For two cameras, at least 7 points are needed

Types of ambiguity Projective 15dof Preserves intersection and tangency Affine 12dof Preserves parallellism, volume ratios Similarity 7dof Preserves angles, ratios of length Euclidean 6dof Preserves angles, lengths With no constraints on the camera calibration matrix or on the scene, we get a projective reconstruction Need additional information to upgrade the reconstruction to affine, similarity, or Euclidean

Projective ambiguity

Projective ambiguity

Affine ambiguity Affine

Affine ambiguity

Similarity ambiguity

Similarity ambiguity

Bundle adjustment Non-linear method for refining structure and motion Minimizing reprojection error Xj P1Xj x3j x1j P3Xj P2Xj x2j P1 P3 P2

Photo synth Noah Snavely, Steven M. Seitz, Richard Szeliski, "Photo tourism: Exploring photo collections in 3D," SIGGRAPH 2006 http://photosynth.net/