30
Harris corner detector Digital Visual Effects, Spring 2005 Yung-Yu Chuang 2005/3/16 with slides by Trevor Darrell Cordelia Schmid, David Lowe, Darya Frolova, Denis Simakov, Robert Collins and Jiwon Kim

Harris corner detector

Embed Size (px)

DESCRIPTION

Harris corner detector. Digital Visual Effects, Spring 2005 Yung-Yu Chuang 2005/3/16. with slides by Trevor Darrell Cordelia Schmid , David Lowe, Darya Frolova, Denis Simakov , Robert Collins and Jiwon Kim. Moravec corner detector (1980). - PowerPoint PPT Presentation

Citation preview

Page 1: Harris corner detector

Harris corner detectorDigital Visual Effects, Spring 2005Yung-Yu Chuang2005/3/16

with slides by Trevor Darrell Cordelia Schmid, David Lowe, Darya Frolova, Denis Simakov, Robert Collins and Jiwon Kim

Page 2: Harris corner detector

Moravec corner detector (1980)• We should easily recognize the point by lookin

g through a small window• Shifting a window in any direction should give

a large change in intensity

Page 3: Harris corner detector

Moravec corner detector

flat

Page 4: Harris corner detector

Moravec corner detector

flat

Page 5: Harris corner detector

Moravec corner detector

flat edge

Page 6: Harris corner detector

Moravec corner detector

flat edgecorner

isolated point

Page 7: Harris corner detector

Moravec corner detectorChange of intensity for the shift [u,v]:

2

,

( , ) ( , ) ( , ) ( , )x y

E u v w x y I x u y v I x y

IntensityShifted intensity

Window function

Four shifts: (u,v) = (1,0), (1,1), (0,1), (-1, 1)Look for local maxima in min{E}

Page 8: Harris corner detector

Problems of Moravec detector• Noisy response due to a binary window function• Only a set of shifts at every 45 degree is considered• Responds too strong for edges because only minim

um of E is taken into account

Harris corner detector (1988) solves these problems.

Page 9: Harris corner detector

Harris corner detector

Noisy response due to a binary window function Use a Gaussian function

Page 10: Harris corner detector

Harris corner detector

Only a set of shifts at every 45 degree is consideredConsider all small shifts by Taylor’s expansion

yxyx

yxy

yxx

yxIyxIyxwC

yxIyxwB

yxIyxwA

BvCuvAuvuE

,

,

2

,

2

22

),(),(),(

),(),(

),(),(

2),(

Page 11: Harris corner detector

Harris corner detector

( , ) ,u

E u v u v Mv

Equivalently, for small shifts [u,v] we have a bilinear approximation:

2

2,

( , ) x x y

x y x y y

I I IM w x y

I I I

, where M is a 22 matrix computed from image derivatives:

Page 12: Harris corner detector

Harris corner detector

Responds too strong for edges because only minimum of E is taken into accountA new corner measurement

Page 13: Harris corner detector

Harris corner detector

( , ) ,u

E u v u v Mv

Intensity change in shifting window: eigenvalue analysis

1, 2 – eigenvalues of M

direction of the slowest chan

ge

direction of the fastest change

(max)-1/2

(min)-1/2

Ellipse E(u,v) = const

Page 14: Harris corner detector

Harris corner detector

1

2

Corner1 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

Classification of image points using eigenvalues of M:

Page 15: Harris corner detector

Harris corner detector

Measure of corner response:

2det traceR M k M

1 2

1 2

det

trace

M

M

(k – empirical constant, k = 0.04-0.06)

Page 16: Harris corner detector

Another view

Page 17: Harris corner detector

Another view

Page 18: Harris corner detector

Another view

Page 19: Harris corner detector

Summary of Harris detector

Page 20: Harris corner detector

Harris corner detector (input)

Page 21: Harris corner detector

Corner response R

Page 22: Harris corner detector

Threshold on R

Page 23: Harris corner detector

Local maximum of R

Page 24: Harris corner detector

Harris corner detector

Page 25: Harris corner detector

Harris Detector: Summary• Average intensity change in direction [u,v] can be e

xpressed 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 Mv

2

1 2 1 2R k

Page 26: Harris corner detector

Harris Detector: Some Properties• Partial invariance to affine intensity change

Only derivatives are used => invariance to intensity shift I I + b

Intensity scale: I a I

R

x (image coordinate)

threshold

R

x (image coordinate)

Page 27: Harris corner detector

Harris Detector: Some Properties• Rotation invariance

Ellipse rotates but its shape (i.e. eigenvalues) remains the sameCorner response R is invariant to image rotation

Page 28: Harris corner detector

Harris Detector is rotation invariant

Repeatability rate:# correspondences

# possible correspondences

Page 29: Harris corner detector

Harris Detector: Some Properties

• But: non-invariant to image scale!

All points will be classified as edges

Corner !

Page 30: Harris corner detector

Harris Detector: Some Properties• Quality of Harris detector for different scale

changes

Repeatability rate:# correspondences

# possible correspondences