XXXIX-B3, 2012
en lines
lap(m,,m,)
h(m,),length(m,))
(9)
e overlap length of
length of line L ,, ang
| the above similarity
vill be used to find out
veen the two lines (Wu
natching lines AC and
es of the end points of
1 using dashed lines in
nes with the lines AC
these two lines can be
ight image
find corresponding
natching
1e overlap segments of
ist in a local buffering
> lines can be used to
inear feature
porting region
on and decomposition
cept of linear feature
4 (a), L is a straight
liscrete image surface.
central axis is L and
the width is 27 , and this rectangular area will be defined as the
linear feature supporting region of line L . As shown in Figure
4 (b), the supporting region can be decomposed into 2r+1
parallel line segments with equal length. L and the left r line
segments are defines as the left linear feature supporting region,
also L and the right r line segments are defines as the right
linear feature supporting region. The gray value of the point J
in the line I will be marked as g T . Arranges the gray values
of (r4 1)xn points in the left supporting region can be arranged
as a matrix form, and then the gray value matrix of the left
linear feature supporting region can be obtained.
Simultaneously, the gray value matrix of the right linear feature
supporting region also can be obtained. On both sides of the to-
be-matched lines, the Normalized Cross Correlation (NCC)
values will be calculated separately between the image gray
values within the supporting region. The larger one is taken as
the final NCC value for this line.Then the correlation
coefficients of the linear feature supporting regions can be
calculated.
Area sim =max(NCC,,NCC,) (10)
Where NCC, . NCC, are the correlation coefficients of
the left and right supporting regions for corresponding lines.
3. EXPERIMENTAL ANALYSIS
This paper adopts the unmanned aerial vehicle images and UCX
digital aerial images to carry on the experiments of line
matching.
31 Experiment 1
The experiment data are two images cut from the stereopair
imaged by unmanned aerial vehicle, and the image sizes both
are 512X 512 pixels. Fig. 5(a) is the target image, and Fig. 5(b)
is the searching image.
(1) Computation of the homograph matrix.
In this step, it firstly realizes the image matching based on
feature points, and the succeed matched corners in the
stereopair images are shown as Fig. 5(c). Then substitutes the
matched points to the equation group LH = 0, obtains the
: : ; T ; ,
coefficient matrix L , and computes the matrix L L . Finally it
solves the homograph matrix Æ through the Singular Value
Decomposition about matrix rr (Wang Jinquan, 2008).
1.0181 0.04434 -3.6743
H =| 0.006193 1.064 42.29 (11)
7.3797e-006 0.000117 1
(2) Line extraction and matching
This paper adopts the Canny edge detection operator to carry on
the edge detection of image, and gets the binarization edge
image. Then it extracts the lines from the binarization edge
Image using the improved Hough Transform. By
setting the threshold, it avoid the over connection problem
for long-distance points, and filters out some
short straight lines. The line extraction results are shown as
Fig. 5(d) and Fig. 5(e). Using the computed homograph matrix
; It projects the line set in Fig. 5(d) to the image coordinate
System defined by the searching image, and the overlap results
International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, Volume XXXIX-B3, 2012
XXII ISPRS Congress, 25 August — 01 September 2012, Melbourne, Australia
of two line sets are shown as Fig. 5(f). This paper determines
the candidate lines according to the distances between the lines
to be matched, and fixes the homologous lines using other
constraint conditions, then obtains the matching results are
shown as Fig. 5(p) and Fig. 5(q). Through the visual
interpretation, the ^ one-to-multiple " phenomenon can be
found in the matching results, which is due to the broken lines
in the extraction, and belongs to the correct matching results.
From this experiment it can be found that the homograph matrix
carries on the effective constraint to the line matching, reduces
the complexity of matching algorithm, and improves the
accuracy rate of matching.
(a) The target image
(c) (left) The positions of points matched in the two images
(d) (right) The results of extracting lines in the target image
(e) (left) The results of extracting lines in the searching image
(f) (right) The fitting of the two sets of straight line segments
(p) (left) The straight lines matched in the target image
(q) (right) The straight lines matched in the searching image
Figure 5. The original images and the results of post-processing