Title: Image Primitives and Correspondence
1 Image Primitives and Correspondence
Jana Kosecka cs223b
2Image 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
3Image Primitives and Correspondence
Difficulties ambiguities, large changes of
appearance, due to change Of viewpoint,
non-uniquess
4Matching - Correspondence
radiance
Lambertian assumption
Rigid body motion
Correspondence
5Local Deformation Models
- Translational model
- Affine model
- Transformation of the intensity values taking
into account occlusions - and noise
6Feature Tracking and Optical Flow
- RHS approximation by the first two terms of
Taylor series
- Brightness constancy constraint
7Aperture Problem
Given brightness constancy constraint at single
point all we can recover is normal flow
8Optical Flow
- Integrate around over image patch
9Optical 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
10Optical Flow
- Previous method - assumption locally constant
flow
- Alternative regularization techniques (locally
smooth flow fields, - integration along contours)
- Qualitative properties of the motion fields
11Point 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)
12Harris Corner Detector - Example
13Feature Selection
- Compute Image Gradient
- Compute Feature Quality measure for each
pixel - Search for local maxima
Feature Quality Function
Local maxima of feature quality function
14Feature Tracking
- Translational motion model
- Closed form solution
- Build an image pyramid
- Start from coarsest level
- Estimate the displacement at the coarsest level
- Iterate until finest level
15Coarse to fine feature tracking
0
1
2
- compute
- warp the window in the second image by
- update the displacement
- go to finer level
- At the finest level repeat for several
iterations
16Affine feature tracking
Intensity offset
Contrast change
17Tracked Features
18Structure and Motion Recovery from Video
1. Use multiple image stream to compute the
information about camera motion and 3D structure
of the scene 2. Tracking image features over time
Tracked Features
Original sequence
19Structure and Motion Recovery from Video
Computed model 3D coordinates of the feature
points
Original picture
20Wide baseline matching
Point features detected by Harris Corner detector
21Region based Similarity Metric
- Sum of squared differences
- Normalize cross-correlation
- Sum of absolute differences
22NCC score for two widely separated views
NCC score