Corner and Interest Point Detection
-
Upload
hailin-arumiga -
Category
Documents
-
view
237 -
download
0
Transcript of Corner and Interest Point Detection
-
7/27/2019 Corner and Interest Point Detection
1/46
Copyright 2012 Elsevier Inc. All rights reserved.
.
Chapter 6
Corner and Interest Point
Detection
-
7/27/2019 Corner and Interest Point Detection
2/46
6.2 Template Matching
The suitable templates for corner templateshave the general appearance of corners:
The complete set of eight templates would be
generated by successive 90 degree rotation of
the above operators.The masks are made to sum to zero , so that
corner detection is insensitive to absolute
changes in light intensity.Copyright 2012 Elsevier Inc. All rights reserved.
.2
4-4-4-
4-54-
555
444
554
554
-
7/27/2019 Corner and Interest Point Detection
3/46
6.3 Second-Order Derivative
Schemes
The corner pixels arise where two relatively
straight-edged fragments intersect.
We consider local variations in image intensity
up to at least second order. Hence, the localintensity variation is expanded as follows:
Copyright 2012 Elsevier Inc. All rights reserved.
.3
-
7/27/2019 Corner and Interest Point Detection
4/46
The symmetrical matrix of second derivatives is:
This gives information on the local curvature at
X0. In fact, a suitable rotation of coordinates
system transforms I(2)into diagonal form:
Where appropriate derivatives have been
reinterpreted as principal curvature at X0.Copyright 2012 Elsevier Inc. All rights reserved.
.4
-
7/27/2019 Corner and Interest Point Detection
5/46
We are particularly interested in rotationallyinvariant operators and obtain the Beaudet
(1978) operators:
The Laplacian operators give significant
responses along lines and edges.
DET operators gives significant signals in the
vicinity of corners.
Copyright 2012 Elsevier Inc. All rights reserved.
.5
-
7/27/2019 Corner and Interest Point Detection
6/46
Copyright 2012 Elsevier Inc. All rights reserved.
.
FIGURE 6.1
-
7/27/2019 Corner and Interest Point Detection
7/46
KR corner detector (Kitchen and Rosenfeld,
1983).
DN corner detector (Dreschler and Nagel, 1984)
ZH corner detector (Zuniga and Haralick, 1983)
Copyright 2012 Elsevier Inc. All rights reserved.
.7
-
7/27/2019 Corner and Interest Point Detection
8/46
6.4 A Median Filter-Based Corner
Detector
The technique involves applying a median filter to theinput image, and then forming another image that is the
difference between the input and the filtered images.
This difference image contains a set of signals that are
interpreted as local measures of corner strength.The median corner detector gives zero signal if the
horizontal curvature is locally zero.
Corner strength is closely related to corner contrast and
corner sharpness.To summarize, the signal from the median-based corner
detector is proportional to horizontal curvature and to
intensity gradient.
Copyright 2012 Elsevier Inc. All rights reserved.
.8
-
7/27/2019 Corner and Interest Point Detection
9/46
Copyright 2012 Elsevier Inc. All rights reserved.
.
FIGURE 6.2
FIGURE 6.2(a) Contours of constant
intensity within a small
neighborhood: ideally, these
are parallel, circular and of
approximately equalcurvature (the contour of
median intensity does not
pass through the center of
the neighborhood); (b) cross-
section of intensity variation,
indicating how the
displacement D of the
median contour leads to an
estimate of corner strength.
Source: Springer 1988
-
7/27/2019 Corner and Interest Point Detection
10/46
Copyright 2012 Elsevier Inc. All rights reserved.
.
FIGURE 6.3
-
7/27/2019 Corner and Interest Point Detection
11/46
Copyright 2012 Elsevier Inc. All rights reserved.
.
FIGURE 6.4 (1/2)
FIGURE 6.4
Comparison of the median and KR corner detectors: (a) original 128X128
grayscale image; (b) result of applying a median detector; (c) result of
including a suitable gradient threshold; (d) result of applying a KR detector.
The considerable amount of background noise is saturated out in (a) but is
evident from (b). To give a fair comparison between the median and KR
detectors, 5X5 neighborhoods are employed in each case, and
nonmaximum suppression operations are not applied: the same gradient
threshold is used in (c) and (d). Source: Springer 1988
-
7/27/2019 Corner and Interest Point Detection
12/46
Copyright 2012 Elsevier Inc. All rights reserved.
.
FIGURE 6.4 (2/2)
FIGURE 6.4
Comparison of the median and KR corner detectors: (a) original 128X128
grayscale image; (b) result of applying a median detector; (c) result of
including a suitable gradient threshold; (d) result of applying a KR detector.
The considerable amount of background noise is saturated out in (a) but is
evident from (b). To give a fair comparison between the median and KR
detectors, 5X5 neighborhoods are employed in each case, and
nonmaximum suppression operations are not applied: the same gradient
threshold is used in (c) and (d).
Source: Springer 1988
-
7/27/2019 Corner and Interest Point Detection
13/46
6.5 The Harris Interest Point
Operator
The second-order derivative corner detector wasdesigned on the basis that corners are ideal,
smoothly varying differentiable intensity profiles.
The media filter-based detectors were found to
be suitable for processing curved step edges.The Harris operator only takes account of first-
order derivatives of the intensity function.
The Harris operator is defined simply, interms ofthe local components of intensity gradient Ix, Iyin
an image and requires a window region to be
defined and averages are taken over the
window.Copyright 2012 Elsevier Inc. All rights reserved..
13
-
7/27/2019 Corner and Interest Point Detection
14/46
We start by computing the following matrix:
The determinant and trace are used to estimate
the corner signal:
We work the sums of quadratic products ofintensity gradients:
Copyright 2012 Elsevier Inc. All rights reserved.
.14
-
7/27/2019 Corner and Interest Point Detection
15/46
Consider the operation of the detectorfor a
single edge (Fig. 6.5(a))
Next, consider the situation in a corner region(Fig. 6.5(b)):
where l1and l2are the lengths of the two edges
bounding the corner, and g is the edge contrast.
Copyright 2012 Elsevier Inc. All rights reserved.
.15
-
7/27/2019 Corner and Interest Point Detection
16/46
Copyright 2012 Elsevier Inc. All rights reserved.
.
FIGURE 6.5
-
7/27/2019 Corner and Interest Point Detection
17/46
We now find:
Copyright 2012 Elsevier Inc. All rights reserved.
.17
-
7/27/2019 Corner and Interest Point Detection
18/46
The above equation may be interpreted as theproduct of
(1)A strength factor , which depends on the edge
length within the window,
(2)A contrast factor ,
(3)A shape factor , which depends on the
edge sharpness
C is zero for , and is maximum for
Copyright 2012 Elsevier Inc. All rights reserved.
.18
2g
2
sin
and02/
-
7/27/2019 Corner and Interest Point Detection
19/46
Suppose we set L=l1+l2=constant, then l1=L-l2,
which is zero for l2=L/2, at which point l1=l2.
This means that the best way of obtainingmaximum corner signal is to place the corner
symmetrically within the window.
Copyright 2012 Elsevier Inc. All rights reserved.
.19
-
7/27/2019 Corner and Interest Point Detection
20/46
Copyright 2012 Elsevier Inc. All rights reserved.
.
FIGURE 6.6
-
7/27/2019 Corner and Interest Point Detection
21/46
6.5.1 Corner Signals and Shifts for Various
Geometric Configurations
When , this leads to C=0.
When is small ( ), we can go on
increasing L by moving the corner symmetrically.
The optimum is reached exactly as the tip of thecorner reaches the far side of the window (Fig.
6.6(c) ).
The signal will fall when the corner moves
further (Fig. 6.6(d) ).
When , the optimum will still occur when
the tip of the corner lies on the far side of
window (Fig.6.7(a)).Copyright 2012 Elsevier Inc. All rights reserved..
21
0
2/
2/
-
7/27/2019 Corner and Interest Point Detection
22/46
However, further increase of will result in adifferent optimum condition (Fig.6-7(b-d)).
We can see this in the symmetrical case l1=l2,
so reduction of L will reduce and C will fall.
This situation continues until , at which
point C again falls to zero.
Copyright 2012 Elsevier Inc. All rights reserved.
.22
sym
-
7/27/2019 Corner and Interest Point Detection
23/46
Copyright 2012 Elsevier Inc. All rights reserved.
.
FIGURE 6.7
-
7/27/2019 Corner and Interest Point Detection
24/46
The detector places the maximum output signalat the corner of the window in the cases where
the signal is stated to be optimum above.
The shift produced has s size equal to radius a
of a window for small corner angles, as then thetip of the corner is symmetrically placed on the
boundary of the window.
When , simple geometry (Fig.6.8(a))
shows that the shift is given by:
Copyright 2012 Elsevier Inc. All rights reserved.
.24
2/
-
7/27/2019 Corner and Interest Point Detection
25/46
Copyright 2012 Elsevier Inc. All rights reserved.
.
FIGURE 6.8
6 5 2 P f ith C i
-
7/27/2019 Corner and Interest Point Detection
26/46
6.5.2 Performance with Crossing
Points and Junctions
Crossing points (Fig. 6.9 a-b, Fig. 6.10 a):
Eq.(6.17) still applies. However, l1,l2must now
be taken as the sum of the edge lengths in each
of the two main directions.There is an important point to note that along the
two edge directions the signs of the contrast
values both reverse at the crossing point.
When the window is centered at the crossing
point, which is the tip of both constituent corners,
the values of l1and l2 are doubled.
Copyright 2012 Elsevier Inc. All rights reserved.
.26
-
7/27/2019 Corner and Interest Point Detection
27/46
Another relevant factor is that the corner
configuration is now symmetric about the
crossing point.
The global maximum signal must occur whenthere is a maximum length of both edges within
the window, and they must therefore be closely
aligned along the window diameters.
These remarks apply both for and for
oblique crossovers (Fig. 6.9(a, b) and 6.10 a.
Copyright 2012 Elsevier Inc. All rights reserved.
.27
2/
-
7/27/2019 Corner and Interest Point Detection
28/46
Copyright 2012 Elsevier Inc. All rights reserved.
.
FIGURE 6.9
-
7/27/2019 Corner and Interest Point Detection
29/46
T-junction: a more general case in that they are
mediated by three regions with three different
intensities (Fig. 6.9 c-d, and Fig. 6.10b).
To calculate the corner signal, we first
generalize Eq. (6.17) to take into account thefact that one line will have higher contrast than
the other:
Where l1is taken as the straight edge with high
contrast g1, and l2is the straight edge with low
contrast g2.Copyright 2012 Elsevier Inc. All rights reserved..
29
-
7/27/2019 Corner and Interest Point Detection
30/46
Copyright 2012 Elsevier Inc. All rights reserved.
.
FIGURE 6.10
-
7/27/2019 Corner and Interest Point Detection
31/46
Copyright 2012 Elsevier Inc. All rights reserved.
.
FIGURE 6.11 (1/4)
FIGURE 6.11Application of the Harris interest point detector. (a) Original image. (b) Interest
point feature strength
-
7/27/2019 Corner and Interest Point Detection
32/46
Copyright 2012 Elsevier Inc. All rights reserved.
.
FIGURE 6.11 (2/4)
FIGURE 6.11
Application of the Harris interest point detector.
(c) Map of interest points showing only those giving greatest response over a
distance of 5 pixels: (d) their placement in the original image
-
7/27/2019 Corner and Interest Point Detection
33/46
Copyright 2012 Elsevier Inc. All rights reserved.
.
FIGURE 6.11 (3/4)
FIGURE 6.11
Application of the Harris interest point detector.
(e and f) Corresponding results for interest points giving greatest response over
a distance of 7 pixels.
-
7/27/2019 Corner and Interest Point Detection
34/46
Copyright 2012 Elsevier Inc. All rights reserved.
.
FIGURE 6.11 (4/4)
FIGURE 6.11
Application of the Harris interest point detector.
(g and h) Later frames in the sequence (also using maximum responses over a
distance of 7 pixels), showing a high consistency of feature identification,
which is important for tracking purposes. Note that interest points really do
indicate locations of interestXcorners, peoples feet, ends of white road
markings, and castle window and battlement features. Also, the greater the
significance as measured by the pixel suppression range, the greater
relevance the feature tends to have.
-
7/27/2019 Corner and Interest Point Detection
35/46
6.6 Corner Orientation
Orientation information is valuable in
immediately eliminating a large number of
possible interpretations of an image, and hence
of quickly narrowing down the search problemand saving computation.
Once a corner has been located accurately, the
orientation can be estimated by finding the mean
intensity gradient over a small regionsurrounding the corner position, i.e. using the
components Ixand Iy.
Copyright 2012 Elsevier Inc. All rights reserved.
.35
-
7/27/2019 Corner and Interest Point Detection
36/46
Copyright 2012 Elsevier Inc. All rights reserved.
.
FIGURE 6.12
6 7 Local Invariant Feature
-
7/27/2019 Corner and Interest Point Detection
37/46
6.7 Local Invariant Feature
Detectors and Descriptors
Feature detection must be consistent and
repeatable in spite of substantial change of view
point.
Features must embody descriptions of theirlocalities so that there is high probability that the
same physical feature will be positively identified
in each view.
Usually, the number of features of each image is
large (~1000), it is highly important to minimize
the feature matching task,
Copyright 2012 Elsevier Inc. All rights reserved.
.37
-
7/27/2019 Corner and Interest Point Detection
38/46
Broadly speaking, obtaining consistent,repeatable feature detection involves allowing
for and normalizing the variations between
views.
The obvious candidates for normalizing arescale, affine distortion and perspective distortion.
Figure 6.13 shows how various transformations
affect a 2-D shape.
Copyright 2012 Elsevier Inc. All rights reserved.
.38
-
7/27/2019 Corner and Interest Point Detection
39/46
Copyright 2012 Elsevier Inc. All rights reserved.
.
FIGURE 6.13
-
7/27/2019 Corner and Interest Point Detection
40/46
FORMULA
Copyright 2012 Elsevier Inc. All rights reserved.
.40
Euclidean transformation(rotation + translation)
Similarity transformation
(scale)
Affine transformation(stretch + shear)
-
7/27/2019 Corner and Interest Point Detection
41/46
6.7.1 Harris Scale and Affine-Invariant Detectors
and Descriptors
6.7.2 Hessian Scale and Affine-Invariant
Detectors and Descriptions6.7.3 The SIFT OperatorScale Invariant
Feature Transformation
Lowe (2004)
6.7.4 The SURF OperatorSpeed-up Robust
Features
Bay et al. (2006, 2008)
Copyright 2012 Elsevier Inc. All rights reserved.
.41
-
7/27/2019 Corner and Interest Point Detection
42/46
Copyright 2012 Elsevier Inc. All rights reserved.
.
FIGURE 6.15
-
7/27/2019 Corner and Interest Point Detection
43/46
Performance Comparison
Copyright 2012 Elsevier Inc. All rights reserved.
.43
Standard Repeatability Criterion:
Other Criteria:
-
7/27/2019 Corner and Interest Point Detection
44/46
Copyright 2012 Elsevier Inc. All rights reserved.
.
Table 6.1
-
7/27/2019 Corner and Interest Point Detection
45/46
Copyright 2012 Elsevier Inc. All rights reserved.
.
Table 6.2
-
7/27/2019 Corner and Interest Point Detection
46/46
Conclusion
Scale invariant operators can normally be dealt
with adequately by a robustness capability for
viewpoint changes of less than 30 degree.
In different applications, different feature
properties may be important, and thus successdepends largely on appropriate selection of
features.
Repeatability may not always be the most
important feature performance characteristics.
There is a need for work focusing on
complementarity of features.