CMRT09: Object Extraction for 3D City Models, Road Databases and Traffic Monitoring - Concepts, Algorithms, and Evaluation
132
5 CONCLUSIONS AND FUTURE WORK
We have developed a generalized variational framework which
addresses large-scale reconstruction through information fusion
and competing grammar-based 3D priors. We have argued that
our inferential approach significantly extends previous 3D ex
traction and reconstruction efforts by accounting for shadows,
occlusions and other unfavorable conditions and by effectively
narrowing the space of solutions due to our novel grammar rep
resentation and energy formulation. The successful recognition-
driven results along with the reliable estimation of buildings 3D
geometry suggest that the proposed method constitutes a highly
promising tool for various object extraction and reconstruction
tasks.
Our a framework can be easily extended to process spectral infor
mation, by formulating respectively the region descriptors and to
account for other types of buildings or other terrain features. For
real-time applications, the labeling function straightforwardly al
lows a parallel computing formulation by concurrently recover
ing the transformations for every region. In order to address the
sub-optimality of the obtained solution, the use of the compressed
sensing framework by collecting a comparably small number of
measurements rather than all pixel values is currently under in
vestigation. Last, but not least introducing hierarchical procedu
ral grammars can reduce the complexity of the prior model and
provide access to more efficient means of optimization.
ACKNOWLEDGEMENTS
This work has been partially supported from the Conseil Gen
eral de Hauts-de-Seine and the Region Ile-de-France under the
TERRA NUMERICA grant of the Pole de competitivite CapDig-
ital.
REFERENCES
Baltsavias, E., 2004. Object extraction and revision by image
analysis using existing geodata and knowledge: current status
and steps towards operational systems. ISPRS Journal of Pho-
togrammetry and Remote Sensing 58, pp. 129-151.
Brenner, C., 2005. Building reconstruction from images and laser
scanning. International Journal of Applied Earth Observation and
Geoinformation 6, pp. 187-198.
Dick, A. R., Torr, P. H. S. and Cipolla, R., 2004. Modelling and
interpretation of architecture from several images. International
Journal of Computer Vision 60(2), pp. 111-134.
Drauschke. M., Schuster, H.-F. and Forstner, W., 2006. De-
tectibility of buildings in aerial images over scale space. In:
ISPRS Symposium of Photogrammetric Computer Vision, Vol.
XXXVInumber Part 3, pp. 7-12.
Forlani, G., Nardinocchi, C., Scaioni, M. and Zingaretti, P, 2006.
Complete classification of raw LIDAR data and 3D reconstruc
tion of buildings. Pattern Anal. Appl. 8(4), pp. 357-374.
Hu, J., You, S. and Neumann, U., 2003. Approaches to large-
scale urban modeling. IEEE Computer Graphics and Applica
tions 23(6), pp. 62-69.
Jaynes, C., Riseman, E. and Hanson, A., 2003. Recognition and
reconstruction of buildings from multiple aerial images. Com
puter Vision and Image Understanding 90(1), pp. 68-98.
Karantzalos, K. and Paragios, N., 2009. Recognition-Driven 2D
Competing Priors Towards Automatic and Accurate Building De
tection. IEEE Transactions on Geoscience and Remote Sensing
47(1), pp. 133-144.
Kim, Z. and Nevada, R., 2004. Automatic description of complex
buildings from multiple images. Computer Vision and Image Un
derstanding 96(1), pp. 60-95.
Lafarge, F., Descombes, X., Zerubia, J. and Pierrot-Deseilligny,
M., 2007. 3D city modeling based on hidden markov model.
In: Proc. IEEE International Conference on Image Processing
(ICIP), Vol. II, pp. 521-524.
Matei, B.C.and Sawhney, H., Samarasekera, S., Kim, J. and Ku
mar, R., 2008. Building segmentation for densely built urban re
gions using aerial lidar data. In: IEEE Conference on Computer
Vision and Pattern Recognition, pp. 1-8.
Mayer, H., 2008. Object extraction in photogrammetric computer
vision. ISPRS Journal of Photogrammetry and Remote Sensing
63(2), pp. 213-222.
Meidow, J. and Schuster, H., 2005. Voxel-based quality evalua
tion of photogrammetric building acquisitions. In: ISPRS Inter
national archives of photogrammetry, remote sensing and spatial
information sciences (Stilla U, Rottensteiner F, Hinz S (Eds)),
Vol. XXXVI, Part 3AV24.
Muller, P, Wonka, P, Haegler, S., Ulmer, A. and Gool, L., 2006.
Procedural modeling of buildings. Proceedings of ACM SIG-
GRAPH / ACM Transactions on Graphics 25(3), pp. 614-623.
Muller, P., Zeng, G., Wonka, P. and Gool, L., 2007. Image-
based procedural modeling of facades. Proceedings of ACM SIG-
GRAPH 2007 / ACM Transactions on Graphics.
Paparoditis, N., Souchon, J.-P., Martinoty, G. and Pierrot-
Deseilligny, M., 2006. High-end aerial digital cameras and their
impact on the automation and quality of the production workflow.
ISPRS Journal of Photogrammetry and Remote Sensing 60(6),
pp. 400-412.
Paragios, N., Chen, Y. and Faugeras, O., 2005. Handbook of
Mathematical Models of Computer Vision. Springer.
Rottensteiner, F., Trinder, J., Clode, S. and Kubik, K., 2007.
Building detection by fusion of airborne laser scanner data and
multi-spectral images: Performance evaluation and sensitivity
analysis. ISPRS Journal of Photogrammetry and Remote Sensing
62(2), pp. 135-149.
Sargent, I., Harding, J. and Freeman, M., 2007. Data Quality in
3D: Gauging Quality Measures From Users’ Requirements. In:
International Symposium on Spatial Quality, Endchede, Nether
lands.
Sohn, G. and Dowman, I., 2007. Data fusion of high-resolution
satellite imagery and LiDAR data for automatic building extrac
tion. ISPRS Journal of Photogrammetry and Remote Sensing
62(1), pp. 43-63.
Suveg, I. and Vosselman, G., 2004. Reconstruction of 3D build
ing models from aerial images and maps. ISPRS Journal of Pho
togrammetry and Remote Sensing 58, pp. 202-224.
Verma, V., Kumar, R. and Hsu, S., 2006. 3D building detection
and modeling from aerial lidar data. In: IEEE Conference on
Computer Vision and Pattern Recognition, pp. 2213-2220.
Wilczkowiak, M., Sturm, P. and Boyer, E., 2005. Using geo
metric constraints through parallelepipeds for calibration and 3D
modeling. IEEE Transactions on Pattern Analysis and Machine
Intelligence 27(2), pp. 194-207.
Zebedin, L., Bauer, J., Kamer, K. and Bischof, H., 2008. Fusion
of feature-and area- based information for urban buildings mod
eling from aerial imagery. In: European Conference on Computer
Vision, Vol. 5305, Lecture Notes in Computer Science, pp. 873-
886.
Zhu, Z. and Kanade (Eds.), T., July, 2008. Special Issue: Model
ing and Representations of Large-Scale 3D scenes. International
Journal of Computer Vision.
