letection rate was 
nisdetections were 
iental map figures 
1ggests that even a 
d by this method. 
with highly dark 
e (i.e. half-hipped 
few misdetections 
sults indicate the 
raction with the 
pes of buildings. 
ldings with weak 
ground, and partly 
»uilt buildings, the 
[isdetections were 
other buildings so 
l, and colored too 
e detections were 
sults indicate that 
roof surfaces with 
n, were extracted 
  
ity, Japan). 
id newly-built 
amine) 
  
Detection Misdetection ; False detection 
rate rate rate 
  
Existing | 89% (=436/490) 111% (—54/490) ;- 
  
Changed | - 11% (=54/490) 
  
  
Newly- | 83% (#19/23) 17% (=4/23) 35% (=8/23) 
built 
  
  
  
  
  
Table 2. Overall accuracy of the result using proposed method 
4.2.2 Comparison with previous method: Both Table 3 
and Figure 10 show a comparison of the result by the proposed 
and previous methods. The results indicate that proposed 
method improves the accuracies in both existing/changed 
building recognition and newly-built building extraction. For 
the existing and changed building recognition, in the previous 
method, when the region segmentation process failed, the 
buildings tended to be misdetected as the region of the 
buildings was expanded. However, in the proposed method, 
buildings were correctly detected as existing buildings, even 
the weak edges can be extracted as a boundary if they locate in 
the right position as well as right direction. For the newly-built 
building detection, in the previous method, a lot of parking or 
open space whose boundary was similar to nearby buildings 
was extracted as candidate regions. However, in the proposed 
method, while the types of target buildings were extended to 
those with combination of bright and dark colored roofs or 
those with different shapes from nearby buildings, the 
detection results were reasonably stable and reliable. 
Those results are much better than those of the previous 
method while using actual high resolution satellite imagery and 
detection of various types of target buildings. Therefore, the 
validity of the proposed method was confirmed. The proposed 
method has been applied to an actual building change detection 
service named "HouseDiff' (Carroll, 2001) as a part of 
recognition engine, and succeeded in assisting users such as 
local governments to maintain highly accurate, up-to-date 
building data. 
    
ee (b) 
Figure 10. Comparison of results. (a)The previous method. 
(b)The proposed method. (yellow=existing, red=changed, 
blue-newly-built) 
  
Previous | Proposed | Improve- 
method | method | ment rate 
  
  
  
  
  
  
  
Existing (correct detection) 32 35 +9.4% 
Changed (false detection) 4 1 -75.0% 
Newly-built(false detection) 16 1 -93.8% 
  
  
Table 3. Result assessment of previous and proposed methods 
75 
5. CONCLUSIONS 
This paper has presented a map-based building change 
detection algorithm using geometric optimization method, 
which consists of the building recognition based on a 
combinatorial optimization method and the newly-built 
building extraction based on an optimal building hypothesis 
search method. The experimental results indicate the 
effectiveness of the methods to integrate bottom-up and top- 
down analysis to achieve highly accurate building change 
detection in urban area, and confirmed the validity of the 
method while using actual QuickBird high resolution satellite 
imagery and detection of various types of target buildings. The 
method was applied to an actual building change detection 
service named "HouseDiff' and succeeded in assisting users. 
Further research should include improvement of the robustness 
of the algorithms by applying pattern recognition and machine 
learning methods to expand the HouseDiff service widely. 
REFERENCES 
Carroll, R. W., 2001. Detecting Building Changes through 
Imagery and Automatic Feature Processing. In: Proc. of 2001 
URISA Annual Conference, California, USA. 
Fischer, A. Kolbe; T. H., T. Lang, F,, Cremers, A. B., 
Fórstner, W., Plümer, L., and Steinhage, V., 1998. Extracting 
Buildings from Aerial Images using Hierarchical Aggregation 
in 2D and 3D. Computer Vision and Image Understanding, 
72(2), pp.185-203. 
Guo, T., and Kazama, Y., 2010. Towards automation of 
building damage detection using WorldView-2 satellite image: 
the case of the Haiti earthquake. In: Proc. of Earth Resources 
and Environmental Remote Sensing/GIS Applications, SPIE 
Vol.7831, 783108. 
Huertas, A., and Nevatia, R., 1998. Detecting Changes in 
Aerial Views of Man-Made Structures. In: Proc. of Sixth 
International Conference on Computer Vision (ICCV '98), 
pp.73-80. 
Ishimaru, N., and Iwamura, K., 2005. An integrated framework 
for map generation by analyzing hyperspectral imagery. In: 
Proc. of IEEE International Geoscience and Remote Sensing 
Symposium (IGARSS '05), Vol.6, pp.3772-3775. 
Kazama, Y., and Guo, T., 2010. House damage assessment 
based on supervised learning method: case study on Haiti. In: 
Proc. of Inage and Signal Processing for Remote Sensing XVI, 
SPIE Vol.7830, 78301F. 
Ogawa, Y., Iwamura, K., and Nomoto, Y., 1999. A map-based 
approach for extracting buildings from aerial images. In: The 
International Archives of Photogrammetry and Remote Sensing, 
Onuma, Japan, Vol.XXXII, Part.5-3W12, pp.29-36. 
ACKNOWLEDGEMENTS 
The authors would like to thank Dr. Tao Guo from Hitachi 
Central Research Laboratory for many and valuable discussions 
and comments. The authors also would like to thank Mr. 
Fuminobu Komura for his kind support and encouragement.