x —
DETECTION OF COLLAPSED BUIDINGS DUE TO EATHQUAKE IN URBAN AREAS
M. Sakamoto ^ *, O. Uchida*, T. Doihara*, Y. Kosugi 5
"R & D Department, Asia Air Survey Co., Ltd., 1-2-2, Manpukuji, Asao-ku, Kawasaki-shi, Kanagawa 215-0004,
Japan - (mi.sakamoto, os.uchida, ta.doihara)@ajiko.co.jp
" Interdisciplinary Graduate School of Science & Engineering, Tokyo Institute of Technology, 4259 Nagatsuta-cho,
Midori-ku, Yokohama 226-8503, Japan - kosugi@pms.titech.ac.jp
PS, WG I1[/4
KEY WORDS: Change Detection, Disaster, Mapping, Matching, Registration, Organization, Rectification, Urban
ABSTRACT:
As the initial investigation on disaster occurrence, it is very important for reducing economical losses to obtain timely observation of
damages especially in metropolis. In such situation, information on changed area obtained from aerial photo analysis is promising.
In this study, we propose a change detection approach objected for metropolis right after the disaster with automatic image
processing of aerial photos. We introduce two different types of approaches. The first method is for the case of no available
orientation information. In this case change detection is performed by registration of images, which are taken before and after the
disaster. We define this approach as 2D image matching method. The second approach aims at acquiring not only 2D changes’
distribution but also quantitative 3D shifts by matching between digital terrain data and images before and after the disaster. We call
this approach 3D image matching method.
In the first step of 2D image matching method, initial registration is executed for minimizing the matching process between images
before and after disaster. This process is performed automatically by detecting appropriate conjugate points which candidates are
derived from images independently with the improved relaxation method and a mathematical model, which is constrained by a
photogrammetric principle (relative orientation). In the next step, image rectification is executed. Owing to these processes y-
parallax in images is eliminated and matching process is restricted in x-axis. In the case of relative orientation failure, formation of
imaginary stereo model by perspective projection is executed as a substitutive means. For detecting changed area, the adaptive
nonlinear mapping is applied. This method is based on model of self-organization in neural network. The one of the image pair is
mapped to the other by iterative local deformation. Changed areas are detected as inconsistent matching in the mapping process.
On the other hand, the concept of 3D image matching method is to compare not only changed images but also the additional terrain
information created before disaster. In this case, it is assumed that stereoscopic aerial photos and exterior orientation are available.
Former digital terrain data such as DSM or digital maps is transformed based on exterior orientation parameters and 3D matching is
carried out. Changed areas are detected as inconsistent texture or height anomaly.
Evaluation tests were performed with actual aerial photos that were taken right after of the earthquake and several years later
respectively. To evaluate the ability of change detection, the results are compared with those by human interpretation. For
quantitative estimation, ROC (Receiver Operating Characteristic) chart was applied, which plots sequential probability of detection
against probability of false alarm. As a result, 80 % of right change detection was achieved when false alarms were about 30 % in
2D image matching method and 18 % in 3D image matching method respectively.
1. INTRODUCTION before and after of the disaster. We define this approach as 2D
image matching method. The second approach aims at
As the initial investigation on disaster occurrence, it is very acquiring not only 2-dimensional changes’ distribution but also
important for reducing economical losses to obtain timely ^ quantitative 3-dimensional shifts by matching digital terrain
observation of damages especially in metropolis. In such data (vector map data) and stereo images before and after the
situation, information on changed area obtained from aerial
photo analysis is promising. We have conducted a study on
automatic change detection of disaster area by earthquakes as a
part of the national project entitled Special Project for
Earthquake Disaster Mitigation in Urban Area. The purpose of
our team is to establish the technique of prompt and efficient
collection of changed or collapsed area in the early stage of
earthquake occurrence, through automatic change detection
with aerial imageries taken before and after the earthquake.
In this study, we propose two different types of change
detection approaches. The first one is for the case of no
available orientation information for aerial imageries. In this
case change detection is performed by registering images taken
* Corresponding author.
disaster. We call this approach 3D matching method.
In the 2D image matching method, imaginary stereo model is
formed for minimizing and stabilizing the image registration
process before and after the disaster. For detecting changed
area, adaptive nonlinear mapping is applied. It is based on the
model of self-organization in neural network (Kosugi et al.,
2000, 2001a, 2001b; Sakamoto et al., 2001). The one of the
image pair is mapped to the other by iterative local deformation.
Changed areas are detected as inconsistent matching in
mapping process.
On the other hand, the concept of 3D image matching method is
to compare not only changed images but also the additional
terrain information, which is managed and created before
Internati
disaster
stereosc
by GPS
digital
paramet
inconsis
Evaluati
were tak
This stu
by ear
automat
detectio:
because
mission
the flow
occurret
there are
first one
indirect
The assi
(1) For «
1) No
the ea
coord:
(2) For |
1) St
earthq
2) Int:
3)2D
prepai
(Geog
availa
5 Digital ster
(with GP.
Digital im
: a helico
+ (with GPS/IM
haaotausases
Externe
analysi
In the
before
means
not acq
compar
