38, 2012
ose with low
‘0 discriminate
brightness and
mbination with
; indicates the
NDVI value,
les indicate the
greenness and
coarse level
)wing types:
and vegetation,
objects, and
processing. The
rightness and
| mapping the
re 1.
irrelevant
objects
RS
area has been
that the time
this fine level
) details, it is
ctral properties
ear scale space
is adopted here
1e fine objects.
sical profile is
struction with
irst component
1e scale space
a cluster via
1e clusters with
orks with only
asing step of 1
he scale range.
o ignore the
hanges on the
shape indices
rea and object
ilding and road
led back via a
pectral class of
International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, Volume XXXIX-B8, 2012
XXII ISPRS Congress, 25 August — 01 September 2012, Melbourne, Australia
a fine object is decided based on the majority rule of pixel-
based spectral classes within it.
New set of rule is established with regards to fine objects and
their newly derived properties. As the potential damage area can
be delineated from coarse level processing, this fine level
processing mainly focuses in detection of intact building roofs.
First, high NDVI and low NIR values are used here to eliminate
small vegetation and water objects. The other 3 parameters, ie.
pixel-based spectral class, morphological profiles and shape
index, are integrated in a decision-making scheme to decide the
likelihood of an object to be a building. All of them are rescaled
to 1-9. The shape index plays some form of quantitative
measure, i.e. building is often a compact object, whereas the
other two are more like qualitative measures. The higher the
shape index value of an object is, the more likely it is a building
roof. Now, the operator needs to make the final decision in this
multi-criteria evaluation scheme.
Original
image
Boundaries for
fine processing
Morphological profile
Shape index
Pixel-based classification
NDVI Objects
Rule-based analysis
Detected objects
Figure 2. Fine level processing
The fully automatic processing can produce the detected objects
using some predefined thresholds and rules. However, to ensure
a good accuracy, the final step is designed for user's decision
following the experiences that it is still difficult to detect the
damage with current high-resolution satellite images (Ehrlich et
al. 2009, Vu and Ban 2010). This is also the main reason why
the rule-based analysis is chosen in development, which allows
the users to input their knowledge to control the process. An
automated classification, even adopting some complex machine
learning algorithms, still cannot be reliable if the data has their
own limitation.
2.3 Design for parallel implementation
As breaking into 2 levels, a big object formed on coarse level
play as the tertiary to focus fine level processing within its
boundary. The first goal of this design is not to analyse in
details a homogeneous big object and hence, to speed up the
processing. More importantly, the idea behind is to allow a
parallel way of implementation in which the piece of
information within each heterogeneous object will be delegated
to a separate CPU. By this way, both data- and task- based
implementation would be achieved.
In addition, the most computational-time-consuming modules
such as region merging and morphological profile will be
implemented with MPI (Message Passing Interface) in line with
implementing the tsunami damage estimation system
67
(Koshimura et al. 2010). A test on image of different sizes of
those two modules is depicted in Figure 3. Computation time
drastically increases when the image size is 1024x1024 pixels,
especially with region merging. The test used a parameter of 32
for K-mean clustering prior to applying the SRM, which seems
to be unnecessarily many. When an operator has some prior
knowledge about the study area and ensures a limited number of
land-cover classes, the number of classes can be reduced and so
the computation time for region merging does.
As mentioned, the proposed solution is to assist the participants
in the crowd to response to a catastrophe event. Thus, different
implementation methods will be considered and deployed to
suit the platform availability of various operators. The
implementation aspect will be reported in next publication.
*»Morphscale *4r "SRM
— 3000
= 2500
o
» m N
sue
© © ©
& 8 &
ua
e
>
am
>
64x64 128x128 256x256 512x512 1024x1024
Image size
Computation time (seco
Figure 3. Computational time (Morphscale for morphological
profile, SRM for region merging)
3. RESULTS AND DISCUSSION
Ban Nam Ken village, one of the most affected areas due to the
2004 Indian Ocean tsunami was selected as the study area with
a QuickBird image captured on 2 January 2005, about a week
after the tsunami attack. For demonstration of the developed
solution, a portion of 1024x1024 was extracted, containing
various surface types like vegetation, water, intact building roof,
collapsed buildings and open soil, as shown in Figure 4a. The
colour composite of brightness, greenness and homogeneous
indices as the result of coarse level processing is illustrated in
Figure 4b.
8g s *
K: Brightness, G: Greenness, B: Homogeneous
R: NIR, a: Red, B: Green
{a} (b)
Figure 4. (a) False Colour Composite of original QuickBird
image and (b) coarse level result
It is obvious that the bluish areas, i.e. low brightness, low
greenness and high homogenous values, are the homogenous
surface water areas and ignored in further fine processing. The
greenness areas, however, needed to be reconfirmed with NDVI
