surface models for its reconstruction (Baltsavias et al, 
1995). 
A number of extensions to the approach are also conceivable: 
e A combination of surface and CSG primitives should 
be considered to provide a more powerful and flexible 
modeling scheme. 
e The approach is equally applicable to close-range pho- 
togrammetric applications, e.g. for industrial and ar- 
chitectural object reconstruction. The surface model 
database can easily be extended, in particular, to ac- 
commodate com posite surfaces in new domains. 
Current research is focussed on implementing the surface ex- 
traction methodology using CPS object modeling. The full 
potential of CPS modeling is being explored, in particular, 
towards definition of an exhaustive database of primitive sur- 
faces. Investigations into the inclusion of additional contex- 
tual information conveyed by the user are underway. 
ACKNOWLEDGMENTS 
This work was partly completed under the AMOBE project at 
ETH-Zürich, while the author was at SRI International, and 
under the UrbanModeler project at UCT. The financial sup- 
port from ETH, NFP and the URC under Entity 453308 is 
gratefully acknowledged, as is that from all the "amoebe". 
Both Manos Baltsavias and Heinz Rüther caused much an- 
guish with helpful critique and suggestions on a near-final 
draft which, however, vastly improved the outcome. 
BIBLIOGRAPHY 
Baltsavias, E., Mason, S., Stallmann, D., 1995. Use of 
DTMs/DSMs and Orthoimages to Support Building Extrac- 
tion, In: Grün, A., Kübler, O., Agouris, P. (Eds.), Automatic 
Extraction of Man-Made Objects from Aerial and Space Im- 
ages, Birkhauser Verlag, Basel, 199-210. 
Bignone, F., Henricsson, O., Fua, P., Stricker, M., 1996. 
Automatic Extraction of Generic House Roofs from High Res- 
olution Aerial Imagery, Submitted to 
Braun, C., Kolbe, T., Lang, F., Schickler, W., Steinhage, V., 
Cremers, A., Forstner, W., Plimer, L., 1995. Models for Pho- 
togrammetric Building Reconstruction, Visual Computing, to 
appear. 
Dreyfus, H.L., 1992. What Computers Still Can't Do: A 
Critique of Artifical Reason, MIT Press, Cambridge, MA, 354 
pages. 
Forstner, W., 1993. A Future of Photogrammetric Research, 
NGT Geodesia, 93-8: 372-383. 
Fua, P., Hanson, A.J., 1991. An Optimization Framework for 
Feature Extraction, Machine Vision Applications, 4:59-87. 
Haala, N., Hahn, M., 1995. Data Fusion for the Detection 
and Reconstruction of Buildings, In: Grün, A., Kiibler, O., 
Agouris, P. (Eds.), Automatic Extraction of Man-Made Ob- 
Jects from Aerial and Space Images, Birkhauser Verlag, Basel, 
211-220. 
Henricsson, O., 1995. Inferring Homogeneous Regions from 
Rich Image Attributes, In: Grün, A., Kübler, O., Agouris, 
P. (Eds.), Automatic Extraction of Man-Made Objects from 
Aerial and Space Images, Birkhauser Verlag, Basel, 13-22. 
522 
International Archives of Photogrammetry and Remote Sensing. Vol. XXXI, Part B3. Vienna 1996 
Herman, M., Kanade, T., 1986. The 3D Mosaic Scene Un- 
derstanding System. In: Pentland, A. (Ed.), From Pixels to 
Predicates, Ablex Publ. Co., Norwood, N.J., 322-358. 
Hofmann, O., Kaltenecker, A., Müller, F., 1993. Das Flug- 
zeuggestützte, digitale Dreizeilenaufnahme- und Auswertesys- 
tem DPA - erste Erprobungsergebnisse, In: Photogrammetric 
Week '93, Fritsch/Hobbie (Eds.), Wichmann Verlag, 97-108. 
Krabill, W.G., 1989. GPS Application to Laser Profiling and 
Laser Scanning for Digital Terrain Models, In: Proc. 42nd 
Photogram metric Week, Stuttgart, 329-340. 
Lang, F., Schickler, W., 1993.  Semiautomatische 3D- 
Gebudeerfassung aus digitalen Bildern, Zeitschrift fr Photo- 
grammetrie und Fernerkundung, 5/93: 193-200. 
Lin, C.L., Zheng, Q., Chellappa, R., Davis, L.S., Zhang, X., 
1994. Site Model Supported Monitoring of Aerial Images, In: 
Proc. CVPR '94, Seattle, 694-699. 
Mason, S., Streilein, A., 1996. Photogrammetric Reconstruc- 
tion of Buildings for 3D City Models, submitted to SA J. 
Surveying and Mapping. 
McKeown, D.M., McGlone, J.C., 1994. Integration of Photo- 
grammetric Cues into Cartographic Feature Extraction, Proc. 
SPIE, 1944: 2-15. 
Mohan, R., Nevatia, R., 1989. Using Perceptual Organization 
to Extract 3-D Structures, /EEE Trans. on PAMI, 11(11): 
1121-1139. 
Nebiker, S., Carosio, A., 1995. Automatic Extraction and 
Structuring of Objects from Scanned Topographical Maps - 
An Alternative to the Extraction from Aerial and Space Im- 
ages”, In: Grün, A., Kübler, O., Agouris, P. (Eds.), Automatic 
Extraction of Man-Made Objects from Aerial and Space Im- 
ages, Birkhäuser Verlag, Basel, 287-296. 
Sayed, A.N., Mikhail, E.M., 1990. Extraction and Photo- 
grammetric Exploitatin of Features in Digital Images, Tech. 
Report CE-PH-90-7, Purdue University. 
Schickler, W., 1992. Feature Matching for Outer Orientation 
of Single Images Using 3-D Wireframe Control Points, /ntern. 
Arch. of Photog. & Remote Sens., B3(III): 591-598. 
Suetens, P., Fua, P., Hanson, A.J., 1992. Computational 
Strategies for Object Recognition, ACM Computing Surveys, 
24(1): 5-61. 
Weidner, U., Forstner, W., 1995. Towards Automatic Build- 
ing Extraction from High Resolution Digital Elevation Models, 
ISPRS J. Photog. & Remote Sens., 50(4): 38-49. 
   
     
    
   
    
   
    
     
     
    
   
      
   
    
    
    
  
    
   
   
   
    
    
   
    
   
   
    
     
    
    
    
   
  
     
   
    
   
    
KEY | 
ABST 
Image 
implie: 
way of 
it with 
From : 
suppre 
As an 
elimin 
extrac 
Image 
. progre 
slowly 
concej 
road, I 
can be 
for a f 
Anoth 
has to 
Sensi 
are th 
of diff 
et al. 
differe 
has be 
image 
paper 
the us 
semar 
define 
Ing 
of ver 
(i.e. be 
differ 
sugge 
the pe 
gener 
mean 
by co 
Ko 
made 
relati 
lar ob 
as sul 
fact tl 
relati 
has fq