feature extraction: cornerslazebnik/spring11/lec07_corner.pdf · finding corners • key property:...
TRANSCRIPT
![Page 1: Feature extraction: Cornerslazebnik/spring11/lec07_corner.pdf · Finding Corners • Key property: in the region around a corner, idih diimage gradient has two or more dominant directions](https://reader036.vdocuments.net/reader036/viewer/2022071016/5fcf82939436bb64aa783eab/html5/thumbnails/1.jpg)
Feature extraction: Corners
9300 Harris Corners Pkwy, Charlotte, NC
![Page 2: Feature extraction: Cornerslazebnik/spring11/lec07_corner.pdf · Finding Corners • Key property: in the region around a corner, idih diimage gradient has two or more dominant directions](https://reader036.vdocuments.net/reader036/viewer/2022071016/5fcf82939436bb64aa783eab/html5/thumbnails/2.jpg)
Why extract features?• Motivation: panorama stitching
• We have two images – how do we combine them?
![Page 3: Feature extraction: Cornerslazebnik/spring11/lec07_corner.pdf · Finding Corners • Key property: in the region around a corner, idih diimage gradient has two or more dominant directions](https://reader036.vdocuments.net/reader036/viewer/2022071016/5fcf82939436bb64aa783eab/html5/thumbnails/3.jpg)
Why extract features?• Motivation: panorama stitching
• We have two images – how do we combine them?
Step 1: extract featuresStep 2: match featuresStep 2: match features
![Page 4: Feature extraction: Cornerslazebnik/spring11/lec07_corner.pdf · Finding Corners • Key property: in the region around a corner, idih diimage gradient has two or more dominant directions](https://reader036.vdocuments.net/reader036/viewer/2022071016/5fcf82939436bb64aa783eab/html5/thumbnails/4.jpg)
Why extract features?• Motivation: panorama stitching
• We have two images – how do we combine them?
Step 1: extract featuresStep 2: match featuresStep 2: match featuresStep 3: align images
![Page 5: Feature extraction: Cornerslazebnik/spring11/lec07_corner.pdf · Finding Corners • Key property: in the region around a corner, idih diimage gradient has two or more dominant directions](https://reader036.vdocuments.net/reader036/viewer/2022071016/5fcf82939436bb64aa783eab/html5/thumbnails/5.jpg)
Characteristics of good features
• Repeatability• The same feature can be found in several images despite geometric g p g
and photometric transformations
• Saliency• Each feature is distinctive
• Compactness and efficiency• Many fewer features than image pixels
• LocalityLocality• A feature occupies a relatively small area of the image; robust to
clutter and occlusion
![Page 6: Feature extraction: Cornerslazebnik/spring11/lec07_corner.pdf · Finding Corners • Key property: in the region around a corner, idih diimage gradient has two or more dominant directions](https://reader036.vdocuments.net/reader036/viewer/2022071016/5fcf82939436bb64aa783eab/html5/thumbnails/6.jpg)
Applications Feature points are used for:
• Image alignment • 3D reconstruction• Motion tracking
R b t i ti• Robot navigation• Indexing and database retrieval• Object recognition• Object recognition
![Page 7: Feature extraction: Cornerslazebnik/spring11/lec07_corner.pdf · Finding Corners • Key property: in the region around a corner, idih diimage gradient has two or more dominant directions](https://reader036.vdocuments.net/reader036/viewer/2022071016/5fcf82939436bb64aa783eab/html5/thumbnails/7.jpg)
Finding Corners
• Key property: in the region around a corner, i di h d iimage gradient has two or more dominant directionsC t bl d di ti ti• Corners are repeatable and distinctive
C H i d M St h "A C bi d C d Ed D t t “C.Harris and M.Stephens. "A Combined Corner and Edge Detector.“Proceedings of the 4th Alvey Vision Conference: pages 147--151.
![Page 8: Feature extraction: Cornerslazebnik/spring11/lec07_corner.pdf · Finding Corners • Key property: in the region around a corner, idih diimage gradient has two or more dominant directions](https://reader036.vdocuments.net/reader036/viewer/2022071016/5fcf82939436bb64aa783eab/html5/thumbnails/8.jpg)
Corner Detection: Basic Idea
• We should easily recognize the point by looking through a small windowShifti i d i di ti h ld• Shifting a window in any direction should give a large change in intensity
“edge”:no change
“corner”:significant
“flat” region:no change in no change
along the edge direction
significant change in all directions
no change in all directions
Source: A. Efros
![Page 9: Feature extraction: Cornerslazebnik/spring11/lec07_corner.pdf · Finding Corners • Key property: in the region around a corner, idih diimage gradient has two or more dominant directions](https://reader036.vdocuments.net/reader036/viewer/2022071016/5fcf82939436bb64aa783eab/html5/thumbnails/9.jpg)
Corner Detection: MathematicsChange in appearance of window w(x,y)
for the shift [u,v]:
[ ]2
,( , ) ( , ) ( , ) ( , )
x yE u v w x y I x u y v I x y= + + −∑
I(x, y)E(u v)E(u, v)
E(3,2)
w(x, y)
![Page 10: Feature extraction: Cornerslazebnik/spring11/lec07_corner.pdf · Finding Corners • Key property: in the region around a corner, idih diimage gradient has two or more dominant directions](https://reader036.vdocuments.net/reader036/viewer/2022071016/5fcf82939436bb64aa783eab/html5/thumbnails/10.jpg)
Corner Detection: MathematicsChange in appearance of window w(x,y)
for the shift [u,v]:
[ ]2
,( , ) ( , ) ( , ) ( , )
x yE u v w x y I x u y v I x y= + + −∑
I(x, y)E(u v)E(u, v)
E(0,0)
w(x, y)
![Page 11: Feature extraction: Cornerslazebnik/spring11/lec07_corner.pdf · Finding Corners • Key property: in the region around a corner, idih diimage gradient has two or more dominant directions](https://reader036.vdocuments.net/reader036/viewer/2022071016/5fcf82939436bb64aa783eab/html5/thumbnails/11.jpg)
Corner Detection: MathematicsChange in appearance of window w(x,y)
for the shift [u,v]:
[ ]2
,( , ) ( , ) ( , ) ( , )
x yE u v w x y I x u y v I x y= + + −∑
IntensityShifted intensity
Window function intensityfunction
orWindow function w(x,y) =
G i1 i i d 0 id Gaussian1 in window, 0 outside
Source: R. Szeliski
![Page 12: Feature extraction: Cornerslazebnik/spring11/lec07_corner.pdf · Finding Corners • Key property: in the region around a corner, idih diimage gradient has two or more dominant directions](https://reader036.vdocuments.net/reader036/viewer/2022071016/5fcf82939436bb64aa783eab/html5/thumbnails/12.jpg)
Corner Detection: MathematicsChange in appearance of window w(x,y)
for the shift [u,v]:
[ ]2
,( , ) ( , ) ( , ) ( , )
x yE u v w x y I x u y v I x y= + + −∑
We want to find out how this function behaves for small shiftssmall shifts
E(u, v)
![Page 13: Feature extraction: Cornerslazebnik/spring11/lec07_corner.pdf · Finding Corners • Key property: in the region around a corner, idih diimage gradient has two or more dominant directions](https://reader036.vdocuments.net/reader036/viewer/2022071016/5fcf82939436bb64aa783eab/html5/thumbnails/13.jpg)
Corner Detection: MathematicsChange in appearance of window w(x,y)
for the shift [u,v]:
[ ]2
,( , ) ( , ) ( , ) ( , )
x yE u v w x y I x u y v I x y= + + −∑
We want to find out how this function behaves for small shifts
Local quadratic approximation of E(u,v) in the neighborhood of (0 0) is given by the second order
small shifts
neighborhood of (0,0) is given by the second-order Taylor expansion:
⎤⎡⎤⎡⎤⎡ uEEE )00()00(1)00(⎥⎦
⎤⎢⎣
⎡⎥⎦
⎤⎢⎣
⎡+⎥
⎦
⎤⎢⎣
⎡+≈
vu
EEEE
vuEE
vuEvuEvvuv
uvuu
v
u
)0,0()0,0()0,0()0,0(
][21
)0,0()0,0(
][)0,0(),(
![Page 14: Feature extraction: Cornerslazebnik/spring11/lec07_corner.pdf · Finding Corners • Key property: in the region around a corner, idih diimage gradient has two or more dominant directions](https://reader036.vdocuments.net/reader036/viewer/2022071016/5fcf82939436bb64aa783eab/html5/thumbnails/14.jpg)
Corner Detection: Mathematics
[ ]2
,( , ) ( , ) ( , ) ( , )
x yE u v w x y I x u y v I x y= + + −∑
Second-order Taylor expansion of E(u,v) about (0,0):
⎥⎤
⎢⎡⎥⎤
⎢⎡
+⎥⎤
⎢⎡
+≈uEE
vuE
vuEvuE uvuuu )0,0()0,0(][1)0,0(
][)0,0(),( ⎥⎦
⎢⎣⎥⎦
⎢⎣
+⎥⎦
⎢⎣
+≈vEE
vuE
vuEvuEvvuvv )0,0()0,0(
][2)0,0(
][)0,0(),(
[ ] ),(),(),(),(2),( vyuxIyxIvyuxIyxwvuE xu ++−++=∑
[ ]
),(),(),(2),(,
,
vyuxIvyuxIyxwvuE xxyx
uu
yx
++++=
∑
∑[ ]
),(),(),(2),(
),(),(),(),(2,
vyuxIvyuxIyxwvuE
vyuxIyxIvyuxIyxw
xyuv
xxyx
++++=
++−+++
∑
∑
[ ] ),(),(),(),(2,
,
vyuxIyxIvyuxIyxw xyyx
xyyx
uv
++−+++∑
∑
![Page 15: Feature extraction: Cornerslazebnik/spring11/lec07_corner.pdf · Finding Corners • Key property: in the region around a corner, idih diimage gradient has two or more dominant directions](https://reader036.vdocuments.net/reader036/viewer/2022071016/5fcf82939436bb64aa783eab/html5/thumbnails/15.jpg)
Corner Detection: Mathematics
[ ]2
,( , ) ( , ) ( , ) ( , )
x yE u v w x y I x u y v I x y= + + −∑
Second-order Taylor expansion of E(u,v) about (0,0):
⎥⎤
⎢⎡⎥⎤
⎢⎡
+⎥⎤
⎢⎡
+≈uEE
vuE
vuEvuE uvuuu )0,0()0,0(][1)0,0(
][)0,0(),(
0)0,0(E =
⎥⎦
⎢⎣⎥⎦
⎢⎣
+⎥⎦
⎢⎣
+≈vEE
vuE
vuEvuEvvuvv )0,0()0,0(
][2)0,0(
][)0,0(),(
0)0,0(0)0,0(
EE
v
u
∑==
),(),(),(2)0,0(
),(),(),(2)0,0(,
yxIyxIyxwE
yxIyxIyxwE
yyvv
xxyx
uu
∑
∑=
=
),(),(),(2)0,0(,
,
yxIyxIyxwE yxyx
uv
yyyx
∑
∑=
![Page 16: Feature extraction: Cornerslazebnik/spring11/lec07_corner.pdf · Finding Corners • Key property: in the region around a corner, idih diimage gradient has two or more dominant directions](https://reader036.vdocuments.net/reader036/viewer/2022071016/5fcf82939436bb64aa783eab/html5/thumbnails/16.jpg)
Corner Detection: Mathematics
[ ]2
,( , ) ( , ) ( , ) ( , )
x yE u v w x y I x u y v I x y= + + −∑
Second-order Taylor expansion of E(u,v) about (0,0):
⎥⎤
⎢⎡⎥⎥⎤
⎢⎢⎡
≈∑∑ u
yxIyxIyxwyxIyxwvuvuE yx
yxyx
x,,
2 ),(),(),(),(),(][)( ⎥
⎦⎢⎣⎥⎥⎦⎢
⎢⎣
≈∑∑ vyxIyxwyxIyxIyxw
vuvuE
yxy
yxyx
yy
,
2
,
,,
),(),(),(),(),(][),(
0)0,0(E =
0)0,0(0)0,0(
EE
v
u
∑==
),(),(),(2)0,0(
),(),(),(2)0,0(,
yxIyxIyxwE
yxIyxIyxwE
yyvv
xxyx
uu
∑
∑=
=
),(),(),(2)0,0(,
,
yxIyxIyxwE yxyx
uv
yyyx
∑
∑=
![Page 17: Feature extraction: Cornerslazebnik/spring11/lec07_corner.pdf · Finding Corners • Key property: in the region around a corner, idih diimage gradient has two or more dominant directions](https://reader036.vdocuments.net/reader036/viewer/2022071016/5fcf82939436bb64aa783eab/html5/thumbnails/17.jpg)
Corner Detection: MathematicsThe quadratic approximation simplifies to
⎤⎡u⎥⎦
⎤⎢⎣
⎡≈
vu
MvuvuE ][),(
where M is a second moment matrix computed from image derivatives:
2
2( , ) x x yI I IM w x y
⎡ ⎤= ⎢ ⎥
⎢ ⎥∑
de at es
2,
( , )x y x y y
yI I I⎢ ⎥⎢ ⎥⎣ ⎦
∑
M
![Page 18: Feature extraction: Cornerslazebnik/spring11/lec07_corner.pdf · Finding Corners • Key property: in the region around a corner, idih diimage gradient has two or more dominant directions](https://reader036.vdocuments.net/reader036/viewer/2022071016/5fcf82939436bb64aa783eab/html5/thumbnails/18.jpg)
Interpreting the second moment matrix
The surface E(u,v) is locally approximated by a quadratic form. Let’s try to understand its shape.y
⎤⎡⎥⎦
⎤⎢⎣
⎡≈
vu
MvuvuE ][),(
∑ ⎥⎤
⎢⎡
= yxx IIIyxwM
2
)(∑⎥⎥⎦⎢
⎢⎣
=yx yyx III
yxwM,
2),(
![Page 19: Feature extraction: Cornerslazebnik/spring11/lec07_corner.pdf · Finding Corners • Key property: in the region around a corner, idih diimage gradient has two or more dominant directions](https://reader036.vdocuments.net/reader036/viewer/2022071016/5fcf82939436bb64aa783eab/html5/thumbnails/19.jpg)
Interpreting the second moment matrix
First, consider the axis-aligned case (gradients are either horizontal or vertical)
⎤⎡⎤⎡ 2 0λIII
(gradients are either horizontal or vertical)
⎥⎦
⎤⎢⎣
⎡=
⎥⎥⎦
⎤
⎢⎢⎣
⎡=∑
2
1
,2 0
0),(
λλ
yx yyx
yxx
IIIIII
yxwM⎦⎣ yy
If either λ is close to 0, then this is not a corner, so look for locations where both are large.
![Page 20: Feature extraction: Cornerslazebnik/spring11/lec07_corner.pdf · Finding Corners • Key property: in the region around a corner, idih diimage gradient has two or more dominant directions](https://reader036.vdocuments.net/reader036/viewer/2022071016/5fcf82939436bb64aa783eab/html5/thumbnails/20.jpg)
Interpreting the second moment matrix⎤⎡
Consider a horizontal “slice” of E(u, v):
This is the equation of an ellipse
const][ =⎥⎦
⎤⎢⎣
⎡vu
Mvu
This is the equation of an ellipse.
![Page 21: Feature extraction: Cornerslazebnik/spring11/lec07_corner.pdf · Finding Corners • Key property: in the region around a corner, idih diimage gradient has two or more dominant directions](https://reader036.vdocuments.net/reader036/viewer/2022071016/5fcf82939436bb64aa783eab/html5/thumbnails/21.jpg)
Interpreting the second moment matrix⎤⎡
Consider a horizontal “slice” of E(u, v):
This is the equation of an ellipse
const][ =⎥⎦
⎤⎢⎣
⎡vu
Mvu
This is the equation of an ellipse.
RRM ⎥⎦
⎤⎢⎣
⎡= −
2
11
00λ
λDiagonalization of M:
⎦⎣ 20 λThe axis lengths of the ellipse are determined by the eigenvalues and the orientation is determined by R
direction of the
direction of the fastest change
slowest change
(λmax)-1/2
(λ i )-1/2(λmin)
![Page 22: Feature extraction: Cornerslazebnik/spring11/lec07_corner.pdf · Finding Corners • Key property: in the region around a corner, idih diimage gradient has two or more dominant directions](https://reader036.vdocuments.net/reader036/viewer/2022071016/5fcf82939436bb64aa783eab/html5/thumbnails/22.jpg)
Visualization of second moment matrices
![Page 23: Feature extraction: Cornerslazebnik/spring11/lec07_corner.pdf · Finding Corners • Key property: in the region around a corner, idih diimage gradient has two or more dominant directions](https://reader036.vdocuments.net/reader036/viewer/2022071016/5fcf82939436bb64aa783eab/html5/thumbnails/23.jpg)
Visualization of second moment matrices
![Page 24: Feature extraction: Cornerslazebnik/spring11/lec07_corner.pdf · Finding Corners • Key property: in the region around a corner, idih diimage gradient has two or more dominant directions](https://reader036.vdocuments.net/reader036/viewer/2022071016/5fcf82939436bb64aa783eab/html5/thumbnails/24.jpg)
Interpreting the eigenvalues
Classification of image points using eigenvalues of M:
λ2
“Corner”λ d λ l
“Edge” λ2 >> λ1
λ1 and λ2 are large,λ1 ~ λ2;E increases in all directions
λ1 and λ2 are small;E is almost constant in all directions
“Edge” λ1 >> λ2
“Flat” region
λ1
1 2region
![Page 25: Feature extraction: Cornerslazebnik/spring11/lec07_corner.pdf · Finding Corners • Key property: in the region around a corner, idih diimage gradient has two or more dominant directions](https://reader036.vdocuments.net/reader036/viewer/2022071016/5fcf82939436bb64aa783eab/html5/thumbnails/25.jpg)
Corner response function2
21212 )()(trace)det( λλαλλα +−=−= MMR
t t (0 04 t 0 06)
“Corner”R > 0
“Edge” R < 0
α: constant (0.04 to 0.06)
R > 0
|R| ll“Edge” R < 0
“Flat” region
|R| small
region
![Page 26: Feature extraction: Cornerslazebnik/spring11/lec07_corner.pdf · Finding Corners • Key property: in the region around a corner, idih diimage gradient has two or more dominant directions](https://reader036.vdocuments.net/reader036/viewer/2022071016/5fcf82939436bb64aa783eab/html5/thumbnails/26.jpg)
Harris detector: Steps
1. Compute Gaussian derivatives at each pixel2 Compute second moment matrix M in a2. Compute second moment matrix M in a
Gaussian window around each pixel 3 Compute corner response function R3. Compute corner response function R4. Threshold R5 Find local maxima of response function5. Find local maxima of response function
(nonmaximum suppression)
C H i d M St h “A C bi d C d Ed D t t ”C.Harris and M.Stephens. “A Combined Corner and Edge Detector.” Proceedings of the 4th Alvey Vision Conference: pages 147—151, 1988.
![Page 27: Feature extraction: Cornerslazebnik/spring11/lec07_corner.pdf · Finding Corners • Key property: in the region around a corner, idih diimage gradient has two or more dominant directions](https://reader036.vdocuments.net/reader036/viewer/2022071016/5fcf82939436bb64aa783eab/html5/thumbnails/27.jpg)
Harris Detector: Steps
![Page 28: Feature extraction: Cornerslazebnik/spring11/lec07_corner.pdf · Finding Corners • Key property: in the region around a corner, idih diimage gradient has two or more dominant directions](https://reader036.vdocuments.net/reader036/viewer/2022071016/5fcf82939436bb64aa783eab/html5/thumbnails/28.jpg)
Harris Detector: StepsC t RCompute corner response R
![Page 29: Feature extraction: Cornerslazebnik/spring11/lec07_corner.pdf · Finding Corners • Key property: in the region around a corner, idih diimage gradient has two or more dominant directions](https://reader036.vdocuments.net/reader036/viewer/2022071016/5fcf82939436bb64aa783eab/html5/thumbnails/29.jpg)
Harris Detector: StepsFi d i t ith l R>thresholdFind points with large corner response: R>threshold
![Page 30: Feature extraction: Cornerslazebnik/spring11/lec07_corner.pdf · Finding Corners • Key property: in the region around a corner, idih diimage gradient has two or more dominant directions](https://reader036.vdocuments.net/reader036/viewer/2022071016/5fcf82939436bb64aa783eab/html5/thumbnails/30.jpg)
Harris Detector: StepsT k l th i t f l l i f RTake only the points of local maxima of R
![Page 31: Feature extraction: Cornerslazebnik/spring11/lec07_corner.pdf · Finding Corners • Key property: in the region around a corner, idih diimage gradient has two or more dominant directions](https://reader036.vdocuments.net/reader036/viewer/2022071016/5fcf82939436bb64aa783eab/html5/thumbnails/31.jpg)
Harris Detector: Steps
![Page 32: Feature extraction: Cornerslazebnik/spring11/lec07_corner.pdf · Finding Corners • Key property: in the region around a corner, idih diimage gradient has two or more dominant directions](https://reader036.vdocuments.net/reader036/viewer/2022071016/5fcf82939436bb64aa783eab/html5/thumbnails/32.jpg)
Invariance and covariance• We want corner locations to be invariant to photometric
transformations and covariant to geometric transformations• Invariance: image is transformed and corner locations do not changeInvariance: image is transformed and corner locations do not change• Covariance: if we have two transformed versions of the same image,
features should be detected in corresponding locations
![Page 33: Feature extraction: Cornerslazebnik/spring11/lec07_corner.pdf · Finding Corners • Key property: in the region around a corner, idih diimage gradient has two or more dominant directions](https://reader036.vdocuments.net/reader036/viewer/2022071016/5fcf82939436bb64aa783eab/html5/thumbnails/33.jpg)
Affine intensity change
I → a I + b
• Only derivatives are used => invariance to intensity shift I → I + b
• Intensity scaling: I → a I
R RRthreshold
R
x (image coordinate) x (image coordinate)
Partially invariant to affine intensity change
![Page 34: Feature extraction: Cornerslazebnik/spring11/lec07_corner.pdf · Finding Corners • Key property: in the region around a corner, idih diimage gradient has two or more dominant directions](https://reader036.vdocuments.net/reader036/viewer/2022071016/5fcf82939436bb64aa783eab/html5/thumbnails/34.jpg)
Image translation
• Derivatives and window function are shift-invariant
Corner location is covariant w r t translationCorner location is covariant w.r.t. translation
![Page 35: Feature extraction: Cornerslazebnik/spring11/lec07_corner.pdf · Finding Corners • Key property: in the region around a corner, idih diimage gradient has two or more dominant directions](https://reader036.vdocuments.net/reader036/viewer/2022071016/5fcf82939436bb64aa783eab/html5/thumbnails/35.jpg)
Image rotation
Second moment ellipse rotates but its shapeSecond moment ellipse rotates but its shape (i.e. eigenvalues) remains the same
Corner location is covariant w r t rotationCorner location is covariant w.r.t. rotation
![Page 36: Feature extraction: Cornerslazebnik/spring11/lec07_corner.pdf · Finding Corners • Key property: in the region around a corner, idih diimage gradient has two or more dominant directions](https://reader036.vdocuments.net/reader036/viewer/2022071016/5fcf82939436bb64aa783eab/html5/thumbnails/36.jpg)
Scaling
Corner
All points will be classifiedbe classified as edges
Corner location is not covariant to scaling!