The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences. Vol. XXXVII. Part B4. Beijing 2008
Updated High
resolution RS
image
Outdated map
road feature
Ï
Change detection and
revision road feature
T
Updated road
feature result
Figure 2 The flowchart of current map road feature updating
method
Searching for the changed road by current means is manually,
the automatic level is low, and tends to omit changed road.
In this paper, the “revision based on change detection” road
feature updating method is discussed in detail, and the current
road feature updating method is present only for comparing.
2.1 Change detection
In map road updating course, the change detection method is
the key technique. In the process of change detection, image
understanding technique of filtering, registration and
multi-scale template matching are three main steps.
2.1.1 The detection to partial changed or diminished
road
2.1.1.1 Filtering
4) whether the road is partial changed or diminished.
The templates this paper designed are a series of ridge-like
templates with multi-scale in width (Figure 3), they are
one-dimensional templates. g m axis represents template gray
scale, y axis represents the template width, the middle part with
even g m value represents the width of road. The difference of
the width of template and the width of road is a constant. A
series of templates were designed, they are differ in width of
road, the width are respectively 3, 5, 7,..., 25(pixel)..., etc. In
figure 3a, the width of template is 13, the width of road is 3; in
figure 3b, the width of template is 15, the width of road is
5.The template with 3 pixel of road width will get max
matching result with a narrow road in image, and the template
with 25 pixel of road width will get max matching result with a
broad road in image. While the width of a road in image is
unknown, it can be obtained by multi-scale template matching
method.
The road in image may be either bright or dark strip comparing
to the background, two series of templates are designed: the
first series of multi-scale templates are bright ridge-like
(figure.3), and the second series of multi-scale templates are
dark ridge-like (Figure 4). The former match bright road more
efficient, and the latter match dark road more efficient. Whether
the road is bright or dark could be judged by this means.
A g m \
Filter the RS image to enhance the fuzzy texture using Wallis
filter. Wallis filter •'] can increase the contrast and suppress
noise of original RS image, thus it can raise the quality and
accuracy of image feature in template matching.
2.1.1.2 Registration
The registration to the remote sensing image and the outdated
map road feature. After choosing several control points equably
on image and corresponding map, using polynomials rectify
model to do the registration, the accuracy of registration should
reach 1 pixel.
a b
Figure 3 Bright ridge-like multi-scale template
Figure 4 Dark ridge-like multi-scale template
2.1.1.3 Multi-scale template matching
The character of the road in remote sensing image can be
concluded as gray scale, geometry, topology, function and
conjunction or context obligation etc. Among the characters,
gray scale is the most important one, the gray scale of road can
be expressed as linear feature with gray difference between the
sides and the middle, so the ribbon-like (for ideal road) or
ridge-like (for general road) template can be applied to match
the road. This paper takes the outdated road vector as initial
place, to match the updated RS image by multi-scale template
matching method. The results are: 1 2 3
1) The maximum template matching point;
2) the width of the road in image;
3) whether the road in image is bright or dark compare with
the background;
Figure 5 is the overlap of outdated road vector and updated
RS image, the white line represents road vector, the line
between two vector vertexes is a vector segment, and a road
vector is make up of several vector segments. The broken line
represents the direction of template matching, the crosses
represent the max matching point produced by multi-scale
template matching method.
Figure 5 Multi-scale template matching
1220