ime XXXIX-B3, 2012
NGULATION
mail.ncku.edu.tw
)901@msn.com
'ell-known scale invariant
vith high end lap between
Therefore, automation on
thus developed to perform
he need on the input data
veness of the method for
both schemes of Quality
n and measurement with a
ra in Taiwan. Also, high
nsity of 3D object points
fficiently even under the
hat the accuracy of photo
1 in the field of computer
nding pixels in a pair of
he image orientation data
rlapping are known. In
e orientations and object
lock adjustment, which is
quisition (Heipke, 1997).
omation of modern aerial
ition, this paper proposes
1se point cloud matching
information.
D
ure into account, a scale
ed for automatic tie point
m scale invariant feature
belongs to the class of
s two main processing
ypoint matching (Lowe,
Gaussian filtering and
" Gaussian) at different
eme values. Those pixels
| keypoints, described by
128 dimensional vector.
calculate the Euclidean
or on the left image to
ght image, i.e. a pair of
o (the shortest Euclidean
one) is smaller than the
(d. Thus, the one on the
ne on the right image.
int on the left image fails.
th more than one author.
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
The matching and searching operations will be done repeatedly
until all keypoints are processed.
The proposed dense matching strategy is illustrated in Figure 1.
Without the need on priori knowledge on image overlap
information, the first step is to process SIFT keypoint extraction
to obtain the location (abbreviated as Loc.) and descriptor
(abbreviated as Des.) of each kepoint on P input images (P Z
2). The loop number equals to P, namely the number of input
images. Step 2 will be the keypoint matching for C? pairs of
images, and one image pair at each time. Then, the result table
of each image matching pair stores locations (of matched points)
and numbers of the left and right image for every image
matching pair. And Step 3 will be matched point connection via
comparing the locations of matched points, rearranging and
coding all the matched points into numbered result, eventually.
DE Esai
p
Figure 1. Dense point d matching strategy
Figure 2 illustrates the format of temporary tables of matched
point connection. Every table of single image matching pair's
result contains locations (row, column) of matched points on
left and right image, denoted by (ri, cj) and (rg, cg). And the
table of connection result stores location (r,c), point number
(PN) and index value for every tie point in each image, which is
done by means of location matching using the result table of
image matching pair. The index value is used for descriptor
inquiry, namely to inform that the descriptor belongs to the i-th
keypoint on the j-th image. Therefore, the numbered tie points
are connected, if their |Ar|«10 pixels and |Ac|«10 ^ pixels, and
the repeated measurements are eliminated at this step.
Figure 2. Connection of matched points
Figure 3. Method of key point extraction for a large image
Furthermore, in order to increase the operational efficiency
especially for large format image of m x n pixels, e.g. m-12096
and n-11200 for our test aerial images, the input image is first
divided into small sub-images, as shown in Figure 3. Taking the
capacity of the core processing programs executed on the
adopted PC into account, each sub-image of the size 1800 rows
x 1800 columns is used in this study. Then, key points are
69
extracted in each sub-image. All key points extracted in all sub-
images are then merged together to output the results of key
point extraction for the original input image of large format.
2.2 Quality Filtering (QF)
The extremely huge number of key points limits the efficiency
of matching a large number of aerial images with large image
format. In order to reduce the runtime, quality filtering (QF) is
attempting to reserve those key points with best image quality.
The standard deviation G, of gray levels, computed by Eq.(1),
of every keypoint is computed in a local image window of 15 x
15 pixels centered at the keypoint. Generally, Gg stands for the
contrast of the keypoint image. In case of less noise, it also
indicates the amount of texture information (or so-called quality)
on the keypoint.
(DH
G.= Tn -G)
where G,.- the gray value of the (r, c)-th pixel
G = the average of gray values in a 15x15 window
Assuming that the indicator values Gs of all keypoints in one
image are normally distributed, the threshold for the selection
of those best key points will be set to their mean plus standard
deviation of overall indicator values in one image. Thus, only
about 16% key points are reserved for later matching.
Apparently, QF uses a heuristic filtering step based on the
standard deviation of gray-levels to throw away weak keypoints
in uniformly distributed individual sub-images. Since the
indicator value of QF is changeable and the threshold is
adjustable, the goodness and availability of the setting will be
verified by the tests.
Figure 4. Two functions of AFTP: overlap estimation(left), and
searching window prediction (right)
2.3 Affine Transformation Prediction (AFTP)
This method uses AFTP to estimate the overlap area, and to
predict the location of searching window, as shown in Figure 4.
Instead of using original high resolution images, AFTP uses
higher layer images with less number of key points in image
pyramid to perform a fast pre-matching to maintain the
efficiency and determine the necessity of follow-up process
simultaneously. The image size at the top level is assumed to be
about 700 x 700 pixels. If the six affine transformation
parameters of an image matching pair can be calculated with a
proper accuracy by means of least-squares adjustment (LSA),
then these two images are overlapped. The locations of their
corresponding image points are approximately described by the
affine transformation parameters, which can also be utilized for
prediction of searching window. Otherwise, this image
matching pair has no overlap or rare overlap, and it will be
skipped in the follow-up matching process. As long as better
overlapped image matching pairs are processed, the tie points
