Scribd
Upload
214 views27 pages

Harris Corner Detector

The document discusses the Harris corner detector algorithm. It begins by motivating the need for distinctive image features that can be matched across views. Corners are identified as good features because pixel values change significantly if the corner point is shifted in any direction. The Harris corner detector provides a mathematical approach to determine "cornerness" by analyzing the eigenvalues of a matrix derived from image gradients at each point. Points with large eigenvalues in both directions indicate flat regions, while large values in one direction indicate edges. Large values in both directions identify corners. The detector assigns each point a corner response score R based on the eigenvalues to identify corners.

Uploaded by

Black Fenix
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
214 views27 pages

Harris Corner Detector

The document discusses the Harris corner detector algorithm. It begins by motivating the need for distinctive image features that can be matched across views. Corners are identified as good features because pixel values change significantly if the corner point is shifted in any direction. The Harris corner detector provides a mathematical approach to determine "cornerness" by analyzing the eigenvalues of a matrix derived from image gradients at each point. Points with large eigenvalues in both directions indicate flat regions, while large values in one direction indicate edges. Large values in both directions identify corners. The detector assigns each point a corner response score R based on the eigenvalues to identify corners.

Uploaded by

Black Fenix
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 27

Robert Collins

CSE486, Penn State

Lecture 06:
Harris Corner Detector
Reading: T&V Section 4.3

Robert Collins
CSE486, Penn State

Motivation: Matchng Problem

Vision tasks such as stereo and motion estimation require


finding corresponding features across two or more views.

Robert Collins
CSE486, Penn State

Motivation: Patch Matching

Elements to be matched are image patches of fixed size

Task: find the best (most similar) patch in a second image


?
=

Camps, PSU

Robert Collins
CSE486, Penn State

Not all Patches are Created Equal!

Inituition: this would be a good patch for matching, since


it is very distinctive (there is only one patch in the second
frame that looks similar).
?
=
Camps, PSU

Robert Collins
CSE486, Penn State

Not all Patches are Created Equal!

Inituition: this would be a BAD patch for matching, since


it is not very distinctive (there are many similar patches
in the second frame)
?
=
Camps, PSU

Robert Collins
CSE486, Penn State

What are Corners?

They are good features to match!

M.Hebert, CMU

Robert Collins
CSE486, Penn State

Corner Points: Basic Idea

We should easily recognize the point by looking


at intensity values within a small window
Shifting the window in any direction should yield
a large change in appearance.

C.Dyer, UWisc

Robert Collins
CSE486, Penn State

Interactive
demo

Appearance Change in
Neighborhood of a Patch

Robert Collins
CSE486, Penn State

Harris Corner Detector: Basic Idea

Harris corner detector gives a mathematical


approach for determining which case holds.
C.Dyer, UWisc

Robert Collins
CSE486, Penn State

C.Dyer, UWisc

Harris Detector: Mathematics

Robert Collins
CSE486, Penn State

Harris Detector: Intuition

For nearly constant patches, this will be near 0.


For very distinctive patches, this will be larger.
Hence... we want patches where E(u,v) is LARGE.
C.Dyer, UWisc

Robert Collins
CSE486, Penn State

Taylor Series for 2D Functions


First partial derivatives

Second partial derivatives

Third partial derivatives


(Higher order terms)

First order approx

Robert Collins
CSE486, Penn State

Harris Corner Derivation

First order approx

Rewrite as matrix equation

Robert Collins
CSE486, Penn State

Harris Detector: Mathematics

Windowing function - computing a


weighted sum (simplest case, w=1)

C.Dyer, UWisc

Note: these are just products of


components of the gradient, Ix, Iy

Robert Collins
CSE486, Penn State

Intuitive Way to Understand Harris

Treat gradient vectors as a set of (dx,dy) points


with a center of mass defined as being at (0,0).
Fit an ellipse to that set of points via scatter matrix
Analyze ellipse parameters for varying cases

Robert Collins
CSE486, Penn State

M.Hebert, CMU

Example: Cases and 2D Derivatives

Robert Collins
CSE486, Penn State

M.Hebert, CMU

Plotting Derivatives as 2D Points

Robert Collins
CSE486, Penn State

Fitting Ellipse to each Set of Points

M.Hebert, CMU

1~2 = small

1~2 = large

1 large; 2 = small

Robert Collins
CSE486, Penn State

C.Dyer, UWisc

Classification via Eigenvalues

Robert Collins
CSE486, Penn State

C.Dyer, UWisc

Corner Response Measure

Robert Collins
CSE486, Penn State

(0,0)

Corner Response Map


lambda1

R=0
R=28

lambda2

R=65

R=104

R=142

Robert Collins
CSE486, Penn State

Corner Response Map


R < 0 Edge
lambda1
R=0
R=28

|R| small
Flat
lambda2

R=65
R=104

R < 0 Edge

R large
Corner

R=142

Robert Collins
CSE486, Penn State

Corner Response Example

Harris R score.
Ix, Iy computed using Sobel operator
Windowing function w = Gaussian, sigma=1

Robert Collins
CSE486, Penn State

Corner Response Example

Threshold: R < -10000


(edges)

Robert Collins
CSE486, Penn State

Corner Response Example

Threshold: > 10000


(corners)

Robert Collins
CSE486, Penn State

Corner Response Example

Threshold: -10000 < R < 10000


(neither edges nor corners)

Robert Collins
CSE486, Penn State

Harris Corner Detection Algorithm

6. Threshold on value of R. Compute nonmax suppression.


M.Hebert, CMU

You might also like