5% when iterative process is performed. The details may 
also be seen from Shi and Shibasaki(1995). 
We have presented some computational algorithms for 
the purpose of automated house change detection for GIS 
database updating, referring to image segmentation, 
multi-feature based stereo matching, statistical disparity 
voting for ground height estimation and so on. The 
major contribution of our research is that we employed 
the disparity differences or surface discontinuities in 
imagery to detect the significant man-made structures like 
houses and created a computational algorithm for 
estimating the ground height, which opened up a new 
path for automated object recognition. 
The experimental results also show that many of the 3D 
lines which give votes for forming the "ground surface" 
in voting algorithm were found lying on the streets or 
roads. It indicates that we may detect the changes of roads 
by overlaying these 3D lines with existing road database. 
It will be one of our research topics in future. 
7. REFERENCES 
Duda, R. O. and Hart, P. E., 1972. Use of the Hough 
transformation to detect lines and curves in pictures. 
Communications of the ACM , vol. 15, no. 1, pp.11-15. 
Grimson, W. E. L., 1985. Discontinuity detection for 
visual surface reconstruction. CVGIP 30, pp.316-330. 
Haralick, R. M. and Shapiro, L. G., 1985. Image 
segmentation techniques. CVGIP 29, pp. 100-132. 
Lew, M. S., Huang, T. S. and Wong, K., 1994. 
Learning and feature selection in stereo matching. IEEE 
Trans. on PAMI , vol. 16, no. 9, pp.869-881. 
    
(a) Original left image 
784 
Li, D.R. and Shao, J. L., 1994. The wavelet and its 
application in image edge detection. ISPRS J. 
Photogramm. Remote Sensing , vol 49 , pp. 2-11. 
Liow, Y. T., Pavlidis, T., 1990. Use of shadows for 
extracting buildings in aerial images. CVGIP, vol. 49. 
Mallat, S. G., 1992. Singularity detection and processing 
with wavelets. IEEE Trans. IT , vol. 38, pp. 617-643. 
Marapane, S. B. and Trivedi, M. M., 1989. Region-based 
stereo analysis for robotic applications. IEEE T. Sys. 
Man. and Cyber. vol. 19, no. 6, pp.1447-1464. 
Marr, D., Hildreth, E., 1980. Theory of edge detection. 
Proc. Roy. Soc. London, vol.207, pp. 187-217. 
Marr, D., and Poggio, T., 1977. A theory of human 
stereo vision. Artifi. Intell. Lab., Mass. Inst. Technol. 
Cambridge , Mass.. 
McKeown, D. M., 1991. Information fusion in 
cartographic feature extraction from aerial imagery. in : 
Digital Photogrammetric Systems, Wichmann, pp.103- 
110. 
Medioni, G. and Nevatia, R., 1985. Segment-based 
stereo matching. CVGIP, vol.31, pp.2-18. 
Nagao, M. and Matsuyama, T., A Structural Analysis of 
Complex Aerial Photographs, Plienum Press, New York 
and London, 1980. 
Shi, Z. C. and Shibasaki, R., 1994. Wavelet transform 
supported image segmentation. Proc. of the 15th 
ACRS, vol. II, Bangalore, India , pp.I-3-1 to I-3-6. 
    
ARR us Ec: S 
(b) Original right image 
International Archives of Photogrammetry and Remote Sensing. Vol. XXXI, Part B4. Vienna 1996 
  
  
  
Cg "m