CSci 6971: Image Registration Lecture 5: Feature-Base Regisration January 27, 2004 Prof. Chuck Stewart, RPI Dr.
Download
Report
Transcript CSci 6971: Image Registration Lecture 5: Feature-Base Regisration January 27, 2004 Prof. Chuck Stewart, RPI Dr.
CSci 6971: Image Registration
Lecture 5: Feature-Base Regisration
January 27, 2004
Prof. Chuck Stewart, RPI
Dr. Luis Ibanez, Kitware
Overview
What is feature-based (point-based)
registration?
Feature points
The correspondence problem
Solving for the transformation estimate
Putting it all together: ICP
Discussion and conclusion
Image Registration
Lecture 5
2
What is Feature-Based Registration?
Images are described as discrete sets of
point locations associated with a geometric
measurement
Locations may have additional properties
such as intensities and orientations
Registration problem involves two parts:
Finding correspondences between features
Estimating the transformation parameters
based on these correspondences
Image Registration
Lecture 5
3
Feature Examples: Range Data
Range image points:
(x,y,z) values
Triangulated mesh
Surface normals are
sometimes computed
Notice:
Some information
(locations) is
determined directly by
the sensor (“raw data”)
Some information is
inferred from the data
Image Registration
Lecture 5
QuickTime™ and a
TIFF (Uncompressed) decompressor
are needed to see this picture.
4
Feature Examples: Vascular Landmarks
Branching points
pulmonary images:
Lung vessels
Airway branches
Retinal image
branches and
cross-over points
Typically augmented
(at least) with
orientations of
vessels meeting to
form landmarks
Image Registration
Lecture 5
5
Points Along Centers of Vessels and Airways
Airways and vessels
modeled as tubular
structures
Sample points spaced
along center of tubes
Note that the entire
tube is rarely used
as a unit
Augmented
descriptions:
Orientation
Radius
Image Registration
Lecture 5
6
“Interest” Points
Locations of strong
intensity variation in all
directions
Augmented with summary
descriptions (moments) of
surrounding intensity
structures
Recent work in making
these invariant to
viewpoint and
illumination.
We’ll discuss interest
points during Lectures 16
and 17
Image Registration
Lecture 5
Brown and Lowe, Int. Conf. On
Computer Vision, 2003
7
Feature Points: Discussion
Many different possible features
Problem is reliably extracting features in all
images
This is why more sophisticated features are
not used
Feature extraction methods do not use all
intensity values
Use of features dominates range-image
registration techniques where “features” are
provided by the sensor
Image Registration
Lecture 5
8
Preamble to Feature-Based Registration: Notation
Set of moving image features
Set of fixed image features
Each feature must include a point location in
the coordinate system of its image. It may
include more
Set of correspondences
Image Registration
Lecture 5
9
Mathematical Formulation
Error objective function depends on unknown
transformation parameters and unknown feature
correspondences
Each may depend on the other!
Transformation may include mapping of more than
just locations
Distance function, D, could be as simple as the
Euclidean distance between location vectors.
We are using the forward transformation model.
Image Registration
Lecture 5
10
Correspondence Problem
Determine correspondences before estimating
transformation parameters
Based on rich description of features
Error prone
Determine correspondences at the same time as
estimation of parameters
“Chicken-and-egg” problem
For the next few minutes we will assume a set of
correspondences is given and proceed to the
estimation of parameters
Then we will return to the correspondence
problem
Image Registration
Lecture 5
11
Example: Estimating Parameters
2d point locations:
Similarity transformation:
Euclidean distance:
Image Registration
Lecture 5
12
Putting This Together
Image Registration
Lecture 5
13
What Do We Have?
Least-squares objective function
Quadratic function of each parameter
We can
Take the derivative with respect to each
parameter
Set the resulting gradient to 0 (vector)
Solve for the parameters through matrix
inversion
We’ll do this in two forms: component and
matrix/vector
Image Registration
Lecture 5
14
Component Derivative (a)
Image Registration
Lecture 5
15
Component Derivative (b)
At this point, we’ve dropped the leading factor of 2.
It will be eliminated when this is set to 0.
Image Registration
Lecture 5
16
Component Derivatives tx and ty
Image Registration
Lecture 5
17
Gathering
Setting each of these equal to 0 we obtain a
set of 4 linear equations in 4 unknowns.
Gathering into a matrix we have:
Image Registration
Lecture 5
18
Solving
This is a simple equation of the form
Provided the 4x4 matrix X is full-rank
(evaluate SVD) we easily solve as
Image Registration
Lecture 5
19
Matrix Version
We can do this in a less painful way by
rewriting the following intermediate
expression in terms of vectors and matrices:
Image Registration
Lecture 5
20
Matrix Version (continued)
This becomes
Manipulating:
Image Registration
Lecture 5
21
Matrix Version (continued)
Taking the derivative of this wrt the
transformation parameters (we didn’t cover
vector derivatives, but this is fairly
straightforward):
Setting this equal to 0 and solving yields:
Image Registration
Lecture 5
22
Comparing the Two Versions
Final equations are identical (if you expand
the symbols)
Matrix version is easier (once you have
practice) and less error prone
Sometimes efficiency requires handcalculation and coding of individual terms
Image Registration
Lecture 5
23
Resetting the Stage
What we have done:
Features
Error function of transformation parameters
and correspondences
Least-squares estimate of transformation
parameters for fixed set of
correspondences
Next:
ICP: joint estimation of correspondences
and parameters
Image Registration
Lecture 5
24
Iterative Closest Points (ICP) Algorithm
Given an initial transformation estimate 0
t=0
Iterate until convergence:
Establish correspondences:
For fixed transformation parameter estimate, t,
apply the transformation to each moving image
feature and find the closest fixed image feature
Estimate the new transformation
parameters,
For the resulting correspondences, estimate
t+1
ICP algorithm was developed almost simultaneous by at
least 5 research groups in the early 1990’s.
Image Registration
Lecture 5
25
Finding Correspondences
Map feature into coordinate system of If
Find closest point
Image Registration
Lecture 5
26
Finding Correspondences (continued)
Enforce unique correspondences
Avoid trivial minima of objective function
due to having no correspondences
Spatial data structures needed to make
search for correspondences efficient
K-d trees
Digital distance maps
More during lectures 11-15…
Image Registration
Lecture 5
27
Initialization and Convergence
Initial estimate of transformation is again crucial
because this is a minimization technique
Determining correspondences and estimating the
transformation parameters are two separate
processes
With Euclidean distance metrics you can show
they are working toward the same minimum
In general this is not true
Convergence in practice is sometimes problematic
and the correspondences oscillate between points.
Image Registration
Lecture 5
28
2d Retinal Example
White = vessel
centerline points from
one image
Black = vessel
centerline points from
second image
Yellow line segments
drawn between
corresponding points
Because of the
complexity of the
structure, initialization
must be fairly accurate
Image Registration
Lecture 5
29
Comparison
Intensity-Based
Feature-Based
For a given transformation
estimate, we can only find
a new, better estimate, not
the best estimate, based
on the gradient step.
We then need to update
the constraints and reestimate
For given set of
correspondences, we
can directly (leastsquares) estimate the
best transformation
BUT, the transformation
depends on the
correspondences, so
we generally need to reestablish the
correspondences.
Image Registration
Lecture 5
30
Summary
Feature-based registration
Feature types and properties
Correspondences
Least-squares estimate of parameters based
on correspondences
ICP
Comparison
Image Registration
Lecture 5
31
Looking Ahead to Lecture 6
Introduction to ITK and the ITK registration
framework.
Image Registration
Lecture 5
32