(XIX-B3, 2012
its
IN OF ROAD
ng to filtering larger
n the local area the
djusting to smaller
ut the parking lot,
of road that:
ith low intensity in
n not parallel and
get the rough road
areas with a low
itensity connection
; the geometrical
il characteristics we
ng is used to extend
caused by uneven
t local hierarchical
nd get rough road
ased on the road
d according to the
kpoints caused by
ure Filtering
‘or this purpose we
,
j
(ASA) (4)
is the intensity of
the layer , AS is
the layer. Figure 4
ty.
and reduce the
local scope. In the
oy step, and judge
ion. When these
n threshold, judge
tively for deciding
1 next local small
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
Figure 4. Comparison of different intensity
For these areas with the shape are similar circle or square, we
adopt the ratio of the circumference and area as judgment
standard. For square, @ and D are defined as side,
represents area and W represents circumference.
S ab
Do (5)
W 2(a+b)
Because the road is strip shape, so we suppose a > b and
define M= b/ a
2
ma ma mS (6)
2a(l+m) 201m). 204m)
=
W
So the area and perimeter of the road meet the following
conditions:
Vins fut) (7)
S
—— i
W 20m)
From the equation we can see, in case of certain area, the
smaller of m the greater of circumference.
This method can rule out circular area and rectangular area
efficiently, but not good at other strange shape. So a Fourier
descriptor is inducted to eliminate none-road areas.
Fourier descriptor is Fourier transform coefficient of object
boundary curves. It is the frequency domain analysis results
of object boundary curves signal. According to the properties
of the Fourier transformation, Fourier descriptor relates to
scale, direction of shape and curves starting points. Therefore
it's necessary to normalize Fourier descriptor. Through
translation, rotation and scale invariance, normalization
Fourier descriptor can identify the shape of an object. In order
to extract road accuracy, this paper employs simple training
sets for Fourier descriptor.
Through the above constraints, the vast majority of the non-
road region has been eliminated as shown in figure 5. Regions
133
eliminated in the process are stored in addition which will be
used in the following process.
Figure 5. The main road frame
3.2 Region Growing
Most of the none-road area through the above steps has been
excluded. This paper will put these not excluded points as
seed, control and grow through some threshold .The road
regional growth is also in the local, as data quantity is big,
growing in the entire region will produce very high space
complexity and time complexity. In order to be able to
produce more accurate road, the paper will set the value very
small, here set it 4 (in this paper the range of return intensity
is 0-255), the main consideration is a lot of points meet the
conditions produced in the last step .As the threshold set is
smaller, after growing will also have some breakpoints
(mainly due to uneven distribution intensity of the road).This
paper will take judgment methods of number of connection
areas to make up breakpoint. The area removed in the
previous step was preserved in another place, and put the area
back to the road. If you join a "piece", the number of
connection areas decrease, join the piece to road, or deleted it.
The finally result is shown in the figure 6.
a. RYT
| P E p
Figure 6. Road extraction result
4. CONCLUSIONS
In this study, hierarchical extraction algorithm for DTM
generation is proved particularly suitable for the flat regions.
For the fluctuant ground, we can increase the number of
layers to achieve good results. Proposed hierarchical method
of DTM extraction shows high accuracy and low complexity
in the experiments. Local morphological filtering for road
extraction can filtered out these areas which intensity values is
close to the road, for example, the squares, parking lots and so
on. Proposed methods are demonstrated of taking full
advantage of low complexity, stability and widely
applicability.
However, there are some issues that need further study:
1. In this article the geometry judgment effect is not very
ideal, needs further study.
