The upper floor is visible only in small parts of the images, only 
in few images and with a very low resolution with causes 
blurring and thus a very low amount of feature points. A 
necessary improvement would be a prediction of the movement 
of the features. In almost every image there are enough features 
found from the image before to predict a movement of lost 
feature. This predicted features could be search in following 
images. This could improve the density of the point cloud and 
the accuracy in the bundle adjustment. 
Further improvements can be achieved by combining the 
forward looking image sequence with a backward looking 
sequence to reduce occlusions and to add more images showing 
a specific voxel in the 3d model space. 
At the moment we are working on a pssobility to integrate both 
bundle adjustments, the orientation step and the matching step, 
as the given building model with its lines should be usable as 
ground control points in the orientation step directly. 
References 
Avbelj, J., Iwaszczuk, D., Stilla, U., 2010. Matching of 3D 
wire-frame building models with image features from infrared 
video sequences taken by helicopters. PCV 2010 - 
Photogrammetric Computer Vision and Image Analysis. 
International Archives of Photogrammetry, Remote Sensing and 
Spatial Geoinformation Sciences, 38(3B): pp. 149-154 
Fischler, M.A., Bolles, R.C. 1981. Random Sample Consensus: 
A Paradigm for Model Fit-ting with Applications to Image 
Analysis and Automated Cartography. In: Communications of 
the ACM, 24(6), pp. 381-395. 
Foerstner, W. and Guelch, E., 1987. A Fast Operator for 
Detection and Precise Location of Distinct Points, Corners and 
Centers of Circular Features. In: Proceedings of the ISPRS 
Intercommission Workshop on Fast Processing of 
Photogrammetric Data, pp. 281-305. 
Frueh, C., Sammon, R., Zakhor, A., 2004. Automated Texture 
Mapping of 3D City Models With Oblique Aerial Imagery, 
Proceedings of the 2nd International Symposium on 3D Data 
Processing, Visualization, and Transmission (3DPVT'04) 
Haralick, R.M., Joo, H., Lee, C.N., Zhuang, X., Vaidya, V.G. 
and Kim, M.B. 1989. Pose estimation from correspondence 
point data. In: SMC 19(6), pp. 1426-1446 
Haralick, R.M., Lee, C.N., Ottenberg, K. and Nolle M. 1994. 
Review and analysis of solutions of the 3-point perspective pose 
estimation problem, In: International Journal of Computer 
Vision 13(3), pp. 331-356. 
Hartley, R.L. and Zisserman, A., 2003. Multiple View 
Geometry in Computer Vision, In: Cambridge University Press, 
ISBN 0-521-54051-8. 
Heinrichs, M., Hellwich, O., Rodehorst, V. 2008. Robust 
Spatio-Temporal Feature Tracking. In: Chen Jun, Jiang Jie and 
Wolfgang Fórstner: Proc. of the XXI Congress of the Int. 
Society for Photogrammetry and Remote Sensing, Beijing, 
China, International Archives of Photogrammetry and Remote 
Sensing 37(B3a), pp. 51-56 
Iwaszczuk D., Hoegner L., Stilla U., 2011. Detection of 
windows in IR building textures using masked correlation. In: 
Stilla U, Rottensteiner F, Mayer H, Jutzi B, Butenuth M (Eds.) 
   
Photogrammetric Image Analysis, ISPRS Conference . 
Proceedings. Lecture Notes in Computer Science, Vol. 6952, 
Springer: 133-146 
Klingert, M.,2006. The usage of image processing methods for 
interpretation of thermography data ,17th International 
Conference on the Applications of Computer Science and 
Mathematics in Architecture and Civil Engineering, Weimar, 
Germany, 12-14 July 2006. 
Lo, C.P., Quattrochi, D.A.,2003. Land-Use and Land-Cover 
Change, Urban Heat Island Phenomenon, and Health 
Implications: A Remote Sensing Approach, Photogrammetric 
Engineering & Remote Sensing, vol. 69(9), pp. 1053-1063 
Longuet-Higgins, H.C., 1981. A computer algorithm for 
reconstruction a scene from two projections, In: Nature 239, pp. 
133-135. 
Lowe, D., 2004. Distinctive Image Features from Scale- 
Invariant Keypoints. In: International Journal of Computer 
Vision, 60(2), pp. 91-110. 
Mayer, H., 2007. 3D Reconstruction and Visualization of Urban 
Scenes from Uncalibrated Wide-Baseline Image Sequences. In: 
Photogrammetrie — Fernerkundung — Geoinformation 2007(3), 
pp. 167-176. 
Mayer, H. and Reznik, S., 2006. MCMC Linked with Implicit 
Shape Models and Plane Sweeping for 3D Building Facade 
Interpretation in Image Sequences. In: International Archives of 
the Photogrammetry, Remote Sensing and Spatial Information 
Sciences, Vol. (36) 3, pp. 130—135. 
Nistér, D., 2000. Reconstsruction From Uncalibrated Sequences 
with a Hierarchy of Trifocal Tensors. In: Proc. European 
Conference on Computer Vision 2000(1), pp. 649-663 
Nistér, D., 2004. An efficient solution to the five-point relative 
pose problem, In: /EEE Transactions on Pattern Analysis and 
Machine Intelligence 26(6), pp. 756—777 
Pollefeys, M., Nistér, D., Frahm, J. M., Akbarzadeh, A. 
Mordohai, P., Clipp, B., Engels, C., Gallup, D., Kim, S. J, 
Merrell, P., Salmi, C., Sinha, S., Talton, B., Wang, L., Yang, 
Q., Stewénius, H., Yang, R., Welch, G. and Towles, H., 2008. 
Detailed real-time urban 3D reconstruction from video. In: 
International Journal of Computer Vision (IJCV), 78(2-3), 143- 
167. 
Pu, W. and Vosselman, G., 2009. Refining building facade 
models with images. ISPRS Workshop on Object Extraction for 
3D City Models, Road Databases and Traffic Monitoring - 
Concepts, Algorithms and Evaluation (CMRT 09) 
Sirmacek, B., Hoegner, L., and Stilla, U., 2011. Detection of 
windows and doors from thermal images by grouping 
geometrical features, Joint Urban Remote Sensing Event 
(JURSE'l 1), Muenchen, Germany. 
Torr, P. and Murray, D., 1997. The Development and 
Comparison of Robust Methods for Estimating the Fundamental 
Matrix. In: International Journal of Computer Vision 24(3), pp. 
271-300. 
  
    
  
  
   
    
   
    
    
    
    
    
    
   
   
   
    
    
   
    
  
   
   
    
    
   
    
    
    
     
  
    
    
    
     
   
  
   
    
     
  
  
   
  
  
Triggs, 
known 
Compu 
Zhang, 
Uncert: 
Vision