Image Primitives and Correspondence - PowerPoint PPT Presentation

About This Presentation
Title:

Image Primitives and Correspondence

Description:

Document presentation ... Image Primitives and Correspondence Image Primitives and Correspondence Slide 3 Local Deformation Models Feature Tracking and Optical ... – PowerPoint PPT presentation

Number of Views:106
Avg rating:3.0/5.0
Slides: 19
Provided by: Kosta84
Learn more at: https://cs.gmu.edu
Category:

less

Transcript and Presenter's Notes

Title: Image Primitives and Correspondence


1
Image Primitives and Correspondence
Jana Kosecka George Mason University
2
Image Primitives and Correspondence
Given an image point in left image, what is the
(corresponding) point in the right image, which
is the projection of the same 3-D point
3
Matching - Correspondence
Lambertian assumption
Rigid body motion
Correspondence
4
Local Deformation Models
  • Translational model
  • Affine model
  • Transformation of the intensity values and
    occlusions

5
Feature Tracking and Optical Flow
  • Translational model
  • Small baseline
  • RHS approx. by first two terms of Taylor series
  • Brightness constancy constraint

6
Aperture Problem
  • Normal flow

7
Optical Flow
  • Integrate around over image patch
  • Solve

8
Optical Flow, Feature Tracking
Conceptually
rank(G) 0 blank wall problem rank(G) 1
aperture problem rank(G) 2 enough texture
good feature candidates
In reality choice of threshold is involved
9
Optical Flow
  • Previous method - assumption locally constant
    flow
  • Alternative regularization techniques (locally
    smooth flow fields,
  • integration along contours)
  • Qualitative properties of the motion fields

10
Feature Tracking
11
3D Reconstruction - Preview
12
Point Feature Extraction
  • Compute eigenvalues of G
  • If smalest eigenvalue ? of G is bigger than ? -
    mark pixel as candidate
  • feature point
  • Alternatively feature quality function (Harris
    Corner Detector)

13
Harris Corner Detector - Example
14
Wide Baseline Matching
15
Region based Similarity Metric
  • Sum of squared differences
  • Normalize cross-correlation
  • Sum of absolute differences

16
Edge Detection
original image
gradient magnitude
Canny edge detector
  • Compute image derivatives
  • if gradient magnitude gt ? and the value is a
    local maximum along gradient
  • direction pixel is an edge candidate

17
Line fitting
Non-max suppressed gradient magnitude
  • Edge detection, non-maximum suppression
  • (traditionally Hough Transform issues of
    resolution, threshold
  • selection and search for peaks in Hough
    space)
  • Connected components on edge pixels with
    similar orientation
  • - group pixels with common orientation

18
Line Fitting
second moment matrix associated with
each connected component
  • Line fitting Lines determined from eigenvalues
    and eigenvectors of A
  • Candidate line segments - associated line
    quality
Write a Comment
User Comments (0)
About PowerShow.com