Feature Detection and Matching

Reading: Szeliski Chapter 4

Pages: 208~266
http://staff.ustc.edu.cn/~xjchen99/teaching/teaching.html
Image Matching
by Diva Sian
by swashford
TexPoint fonts used in EMF.
Read the TexPoint manual before you delete this box.: AAAAAA
Harder Case
by Diva Sian by scgbt
Even Harder Case
How the Afghan Girl was Identified by Her Iris Patterns Read the story
Harder still?
NASA Mars Rover images
NASA Mars Rover images
with SIFT feature matches
Figure by Noah Snavely
Answer below (look for tiny colored squares)
Features
All is Vanity, by C. Allan Gilbert, 1873-1929
Readings
Szeliski, Ch 4.1
(optional) K. Mikolajczyk, C. Schmid, A performance evaluation of local
descriptors. In PAMI 27(10):1615-1630
- http://www.robots.ox.ac.uk/~vgg/research/affine/det_eval_files/mikolajczyk_
Image Matching
Image Matching
Invariant Local Features
Find features that are invariant to transformations
geometric invariance: translation, rotation, scale
photometric invariance: brightness, exposure,
Feature Descriptors
Advantages of Local Features
Locality
features are local, so robust to occlusion and clutter
Distinctiveness:
can differentiate a large database of objects
Quantity
hundreds or thousands in a single image
Efficiency
real-time performance achievable
Generality
exploit different types of features in different situations
More Motivation
Feature points are used for:
Image alignment (e.g., mosaics)
3D reconstruction
Motion tracking
Object recognition
Indexing and database retrieval
Robot navigation
other
Features
Point/patch,
Edge/curve
Region
Want Uniqueness
Look for image regions that are unusual
Lead to unambiguous matches in other images

How to define unusual?


Corner Detection
Basic idea: Find points where two edges meeti.e., high gradient in two
directions

Cornerness is undefined at a single pixel, because theres only one
gradient per point
Look at the gradient behavior over a small window

Categories image windows based on gradient statistics
Constant: Little or no brightness change
Edge: Strong brightness change in single direction
Flow: Parallel stripes
Corner/spot: Strong brightness changes in orthogonal directions
Matching Criterion
(weighted) Summed Square Difference SSD


Compare an image patch against itself

Local Measures of Uniqueness
Suppose we only consider a small window of pixels
What defines whether a feature is a good or bad candidate?
Slide adapted from Darya Frolova, Denis Simakov, Weizmann Institute.
Feature Detection
flat region:
no change in all
directions
edge:
no change along
the edge direction
corner:
significant change
in all directions
Local measure of feature uniqueness
How does the window change when you shift it?
Shifting the window in any direction causes a big change
Slide adapted from Darya Frolova, Denis Simakov, Weizmann Institute.
Consider shifting the window W by (u,v)
how do the pixels in W change?
compare each pixel before and after by
summing up the squared differences
(SSD)
this defines an SSD error of E(u,v):

Feature Detection: Mathematics
W

Harris Detector: Mathematics
| |
2
,
( , ) ( , ) ( , ) ( , )
x y
E u v w x y I x u y v I x y = + +

Change of intensity for the shift [u,v]:

Intensity
Shifted
intensity
Window
function
or
Window function w(x,y) =
Gaussian 1 in window, 0 outside
Auto-correlation
function
Auto-Correlation Function

Auto-Correlation Function

Good unique minimum 1D aperture problem
No good peak
Taylor Series expansion of I:



If the motion (u,v) is small, then first order approx is good









Small Motion Assumption
Feature Detection: Mathematics
Image gradient
Harris detector with a [-2,-1,0,1,2] filter for Ix
Gaussian filter






Plugging this into the formula on

Small Motion Assumption
| |
2
,
( , ) ( , ) ( , ) ( , )
x y
E u v w x y I x u y v I x y = + +

Feature Detection: Mathematics

W

Feature Detection: Mathematics
This can be rewritten:







x
-
x
+
Auto-correlation matrix
Feature Detection: Mathematics
For the example above
You can move the center of the blue window to anywhere on the
blue unit circle
Which directions will result in the largest and smallest E values?
We can find these directions by looking at the eigenvectors of H

Quick eigenvalue/eigenvector review
The eigenvectors of a matrix A are the vectors x that satisfy:

The scalar is the eigenvalue corresponding to x
The eigenvalues are found by solving:


In our case, A = H is a 2x2 matrix, so we have


The solution:


Once you know , you find x by solving
Feature Detection: Mathematics
This can be rewritten:







Eigenvalues and eigenvectors of H

Define shifts with the smallest and largest change (E value)
x
+
= direction of largest increase in E.

+
= amount of increase in direction x
+
x
-
= direction of smallest increase in E.
- = amount of increase in direction x
+

x
-
x
+
Feature Detection: Mathematics
| |
( , ) ,
u
E u v u v H
v
(
~
(

Intensity change in shifting window: eigenvalue analysis

1
,
2
eigenvalues of H
(
max
)
-1/2
(
min
)
-1/2
Ellipse E(u,v) = const
If we try every possible orientation n,
the max. change in intensity is
2

Feature Detection: Mathematics

2
Corner

1
and
2
are large,

1
~
2
;
E increases in all
directions

1
and
2
are small;
E is almost constant
in all directions
Edge

1
>>
2

Edge

2
>>
1

Flat
region
Classification of image
points using eigenvalues
of M:
Feature Detection: Mathematics
How are
+
, x
+
,
-
, and x
+
relevant for feature detection?
Whats our feature scoring function?


Feature Detection: Mathematics
How are
+
, x
+
,
-
, and x
+
relevant for feature detection?
Whats our feature scoring function?

Want E(u,v) to be large for small shifts in all directions
the minimum of E(u,v) should be large, over all unit vectors [u v]
this minimum is given by the smaller eigenvalue (
-
) of H
Feature Detection
Heres what you do
Compute the gradient at each point in the image
Create the H matrix from the entries in the gradient
Compute the eigenvalues.
Find points with large response (
-
> threshold)
Choose those points where
-
is a local maximum as features

Feature Detection
Heres what you do
Compute the gradient at each point in the image
Create the H matrix from the entries in the gradient
Compute the eigenvalues.
Find points with large response (
-
> threshold)
Choose those points where
-
is a local maximum as features

[Shi and Tomasi 1994]
Harris Detector
Measure of corner response:
( )
2
det trace R M k M =
1 2
1 2
det
trace
M
M


=
= +
(k empirical constant, k = 0.04-0.06)
Harris and Stephens 1988
The trace is the sum of the diagonals, i.e., trace(H) = h
11
+ h
22
Very similar to
-
but less expensive (no square root)
Harris Detector: Mathematics

2
Corner
Edge
Edge
Flat
R depends only on eigenvalues
of H
R is large for a corner
R is negative with large
magnitude for an edge
|R| is small for a flat region
R > 0
R < 0
R < 0 |R| small
Harris Detector
The Algorithm:
Find points with large corner response function R
(R > threshold)
Take the points of local maxima of R
Harmonic Mean




Smoother function in the region where

Brown, M., Szeliski, R., and Winder, S. (2005).
0 1
0 1
det
tr
f


= =
+
H
H
0 1
~
Isocontours of Response

Harris Detector: Workflow
Harris Detector: Workflow
Compute corner response R
Harris Detector: Workflow
Find points with large corner response: R>threshold
Harris Detector: Workflow
Take only the points of local maxima of R
Harris Detector: Workflow
Example: Gradient Covariances
Full image
Detail of image with gradient covar-
iance ellipses for 3 x 3 windows
from Forsyth & Ponce
Corners are where both eigenvalues are big
Example: Corner Detection
(for camera calibration)
courtesy of B. Wilburn
Example: Corner Detection
courtesy of S. Smith
SUSAN corners
Harris Detector: Summary
Average intensity change in direction [u,v] can be expressed as a bilinear
form:



Describe a point in terms of eigenvalues of M:
measure of corner response


A good (corner) point should have a large intensity change in all directions, i.e.
R should be large positive
| |
( , ) ,
u
E u v u v M
v
(
~
(

( )
2
1 2 1 2
R k = +
Outline of Feature Detection
1. Compute the horizontal and vertical derivatives of the image Ix and Iy by
convolving the original image with derivatives of Gaussians (Section
3.2.3).

2. Compute the three images corresponding to the outer products of these
gradients. (The matrix H is symmetric, so only three entries are needed.)

3. Convolve each of these images with a larger Gaussian.

4. Compute a scalar interest measure using one of the formulas discussed
above.

5. Find local maxima above a certain threshold and report them as
detected feature point locations.
Adaptive Non-Maximal Suppression
(ANMS)
Local maxima
Response value should be significantly (10%)
larger than all of its neighbors within a radius
(r)
(a) Strongest 250 (b) Strongest 500
Adaptive Non-Maximal Suppression
(ANMS)

(a) Strongest 250 (b) Strongest 500
(c) ANMS 250, r = 24 (d) ANMS 500, r = 16
Invariance
Suppose you rotate the image by some angle
Will you still pick up the same features?

What if you change the brightness?

Scale?
Invariance
Repeatability of feature detector:
frequency with which keypoints are detected in one image are found
within (=1.5) pixels of the corresponding location in a transformed
image
Scale Invariance
Detect features at a
variety of scales

Multiple resolutions in
a pyramid

Matching in all
possible levels
Multi-Scale Oriented Patches

Scale invariant detection
Suppose youre looking for corners






Feature Detection
Key idea: find scale that gives local maximum of f
f is a local maximum in both position and scale
Common definition of f: Laplacian
Difference between two Gaussian filtered images
with different sigmas

Feature Detection
Stable features in both location and scale
Laplacian of Gaussian (LoG)


Difference of Gaussian

2 2 2 2
2 2
1 2
1 2
1 2

2 2
2 2
1 1 1
2
x y x y
DoG G G e e
o o
o o
t o o
+ +

| |
|
=
|
\ .

Slide from Tinne Tuytelaars
Lindeberg et al, 1996
Slide from Tinne Tuytelaars
Lindeberg et al., 1996







Scale-Space Feature Detection
Empirical number of levels in each octave = 3
1.6 o =
SIFT Feature Detection
Will be explained next week
Rotation Invariance and orientation
estimation
Dominant orientation
Average gradient within a region around the keypoint
(larger window than detection window to make it more
reliable)
Orientation histogram
Affine Invariance
For wide baseline stereo matching or object
recognition
Affine Invariance
For a small enough patch, any continuous image wrapping can
be well approximated by an affine deformation

Eigenvalue analysis for Hessian matrix or auto-correlation:
using the principle axis and ratios to fit the affine coordinate
frame
1 1 2 2
, , , x x
(Lindeberg and Garding 1997; Baumberg 2000; Mikolajczyk and Schmid 2004; Mikolajczyk,
Tuytelaars, Schmid et al. 2005; Tuytelaars and Mikolajczyk 2007)
Affine Invariance
Maximally Stable Extremal Region (MSER)
Matas, Chum, Urban et al. (2004)
Algorithm
Binary regions by thresholding the image at all possible
gray levels
Region area changes as the threshold changes
D_area/D_t is minimal maximal stable

Keypoint Detection
Very active area
(Xiao and Shah 2003; Koethe 2003; Carneiro and Jepson 2005; Kenney, Zuliani, and
Manjunath 2005; Bay, Tuytelaars, and Van Gool 2006; Platel, Balmachnova, Florack
et al. 2006; Rosten and Drummond 2006

Invariance to transformation such as scaling, rotations,
noise, and blur

These experimental results, code, and pointers to the surveyed
papers can be found on their Web site at
http://www.robots.ox.ac.uk/vgg/research/affine/
(Mikolajczyk, Tuytelaars, Schmid et al. 2005)
4.1.2 Feature Descriptor
TBD
SIFT Feature
Scale Invariant Feature Transform (SIFT)
Detect features that densely cover the image
over the full range of scales and locations
Distinctive Image Features from Scale-Invariant Keypoints, David G. Lowe
Points and Patches
Two approaches to finding feature points and
their correspondences
detect in one, then track
For video sequence application, tracking, stereo
Detect independently, then match
For image stitching, recognition
Keypoint Detection and Matching
Four steps:
Feature detection
Feature description
Feature matching
Feature tracking