oT axis
ST)
image
ges of
fferent
lure is
juency
our of
main
nd the
| used
'atures
visible
walls),
mn A
ape of
ree for
essing
CEST)
mages
in the
:d that
in the
omain
mated
are to
k into
encies
'ncies,
object
nostly
‘urther
ilter is
on for
1d the
an be
in the
n, (iii)
in the
tained
011a).
lefault
detect
wever,
or the
well-
dea is
ithout
s very
troyed
ulated
jer of
stance
moment’ (IDM, also known as ‘homogeneity’ ) produced the
best results for man-made objects (Ehlers & Tomowski 2008;
Tomowski et al. 2010). Consequently, these features together
with a bitemporal PCA were used for the CEST method.
3.3 Change Detection Based on Segmentation
Object or segment based image analysis has gained a lot of
interest in the remote sensing community (see, for example,
Otsu 1979 or Blaschke et al. 2008). Segmenting an image
seems to be an excellent pre-analysis tool, especially for images
of very high resolution. Consequently, we developed a
segmentation procedure based on Euclidean distance to be used
for change detection. For each pixel, the Euclidean distance to
each neighboring pixel is calculated. If the distance is below a
threshold, they belong to the same segment. After an
independent segmentation of the images at dates T1 and T2, the
segments of T1 are selected and used also for the T2 image. For
each segment, the T1-T2 correlation coefficient is calculated.
The result is assigned to each pixel in the segment. A new layer
with the result of this segmentation is then created. Segments
with a high correlation represent no changes. Segments with a
low correlation represent changes.
This step is repeated for the opposite direction (i.e., T2-TI
correlation). The results are combined using different
conditional statements. If, for example, the T1 image contains a
number of buildings in a specific area which are not present in
the T2 image, there exists a high probability that this area forms
a large segment in T2 but is split into several small segments in
T1. This would create incorrect change indications. As a final
step, thresholds are used to extract the change segments.
34 Combined Change Detection: The CEST Method
Finally, all three methods are combined in a decision-tree
approach (Fig. 1). The basis for the classification is the result of
the change detection algorithm using edge detection based on
frequency filtering. If the edge parameter indicates ‘no change’,
the pixel in the image is classified as ‘no change’. If the edge
parameter indicates ‘new building’, the pixel is classified as
new, if the texture feature ‘energy’ is an agreement. If energy
indicates ‘change’ and one of the features ‘homogeneity’ or
‘segmentation’ indicate ‘change’, the result is ‘new’. Otherwise,
it is classified as unchanged. If the edge parameter shows
‘change’, it is classified as ‘change’ if the texture feature
‘energy’ coincides. If energy indicates ‘no change’, the pixel
will be classified as ‘no change’. If energy indicates ‘new’ but
the segment and homogeneity parameters show ‘change’, the
pixel is assigned to ‘change’. Otherwise it is classified as
unchanged. The CEST procedure was tested against the
standard change detection methods described above.
3.5 Automatically Created Damage Maps
The produced change images are to a large degree abstract and
hard to interpret. This holds particularly true for people not
accustomed to remote sensing such as members of official
organizations or rescue forces. For the purpose of planning after
a crisis or a catastrophe, the interpretation of change images
should be as easy as possible. An algorithm was developed to
automatically produce a map which can be easily interpreted.
The first step is to generalize the change image. Inside a 20 x 20
pixels window, the amount of change is determined using the
information in the change image. The change percentage of this
area is calculated and then ranked into a number of distinctive
general classes. If less than 15 % of the area has changed, all
International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, Volume XXXIX-B7, 2012
XXII ISPRS Congress, 25 August — 01 September 2012, Melbourne, Australia
pixels are classified as unchanged. Change above 80 % marks
extensive change and change between 15 % and 80 % marks
low to moderate change. Areas of new buildings with a surface
cover of at least 15 % are indicated as ‘new areas’.
Fig. 1. CEST decision tree (description see in the text)
4. STUDY AREA
CEST detection and change map generation methods are now
applied to the selected study sites in Darfur, Sudan. They
represent areas which experienced dramatic changes during the
Darfur conflict. It is estimated that more than 300.000 people
have already died in this conflict and more than 2 million
people have been displaced (http://www .eyesondarfur.org).
Fig. 2 Panchromatic Quickbird-2 images recorded on March 2,
2006 (left — before the attack) and on February 28, 2008 (right-
after the attack) of the town Abu Suruj (2048 x 2048 pixels).
Images courtesy of Digital Globe.
The test area is located in South Darfur and shows part of the
town Abu Suruj in West Darfur (Fig. 2). Because of destroyed
and new settlement areas, this study site is very complex. It
contains changes due to destruction and — at the same time —
changes due to construction. A change detection procedure
should be capable of depicting both types of change. For a more
detailed look at the conditions, Fig. 3 shows subsets of Fig. 2. A
manually digitized change image (black = no change, gray =
destroyed, white = new) which will be used as ‘ground truth’ is
displayed in Fig. 4.
A visual comparison and overlay of the existing man-made
structures shows a high correspondence for both images, so that
a new co-registration was not necessary and the problem of
possible pseudo change was negligible. They were preprocessed
using a histogram matching procedure. An atmospheric
correction is not applied, due to missing ground truth data,
sparse vegetation and only one image band.
