The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences. Vol. XXXVII. Part B7. Beijing 2008 
1188 
5. CONCLUSIONS 
Automated approaches to building detection are important in 
the updating of cadastral maps and monitoring of informal 
settlements. In this paper, a comparative analysis of two data 
fusion and classification approaches, namely Bayesian and 
Dempster-Shafer, as applied to automated building detection in 
aerial data was presented. Results showed that both methods 
perform slightly better in object level than in pixel level. A 
comparison of the performance of the methods revealed that the 
Bayesian maximum likelihood method yields a higher detection 
rate, as compared to the minimum distance method and the 
Dempster-Shafer method; however, the rate of pixels wrongly 
detected as building is also higher in the Bayesian method. In 
practice, the crucial measure in the evaluation a detection 
method is the rate of missed building pixels. In this respect, the 
Bayesian maximum likelihood method was found to have a 
better performance; however, the missed pixels in the 
Dempster-Shafer method were found to be mostly at the 
boundaries of buildings. Therefore, the higher rate of the missed 
building pixels in the Dempster-Shafer method should not be 
seen as a critical drawback of the method. 
In this research, we trained the Dempster-Shafer evidence 
assignment functions using the training regions, and on the 
basis of a trial and error procedure. Further research can be 
focused on developing more elaborated training algorithms for 
the assignment of evidence in the Dempster-Shafer method. 
ACKNOWLEDGEMENTS 
The authors would like to thank the Toposys company for 
providing the dataset that was used in the experiments. 
REFERENCES 
Bartels, M. and Wei, H.,2006. Maximum likelihood 
classification of LIDAR data incorporating multiple co 
registered bands, 4th International Workshop on Pattern 
Recognition in Remote Sensing in conjunction with the 18th 
International Conference on Pattern Recognition, Hong 
Kong, pp. 17-20. 
Brunn, A. and Weidner, U.,1997. Extracting buildings from 
digital surface models, ISPRS Workshop on 3D 
Reconstruction and Modelling of Topographic Objects, 
Stuttgart, pp. 27-34. 
Duda, R.O., Hart, P.E. and Stork, D.G.,2001. Pattern 
classification, second edition. Wiley, New York, 654 pp. 
Fischer, A. et al.,1998. Extracting buildings from aerial images 
using hierarchical aggregation in 2D and 3D. Computer 
Vision and Image Understanding, 72(2): 185-203. 
Fradkin, M., Maitre, H. and Roux, M., 2001. Building 
detection from multiple aerial images in dense urban areas. 
Computer Vision and Image Understanding, 82: 181-207. 
Gordon, J. and Shortliffe, E.H.,1990. The Dempster-Shafer 
theory of evidence. In: G. Shafer and J. Pearl (Editors), 
Readings in uncertain reasoning. Morgan Kaufmann 
Publishers Inc., San Francisco, CA, USA, pp. 768. 
Haala, N. and Brenner, C.,1998. Interpretation of urban 
surface models using 2D building information. Computer 
Vision and Image Understanding, 72(2): 204-214. 
Huertas, A., Lin, C. and Nevada, R.,1993. Detection of 
buildings from monocular views of aerial scenes using 
perceptual organization and shadows, ARPA image 
understanding workshop, Washington, DC, pp. 253-260. 
Khoshelham, K., Li, Z.L. and King, B.,2005. A split-and- 
merge technique for automated reconstruction of roof planes. 
Photogrammetric Engineering and Remote Sensing, 71(7): 
855-862. 
Lin, C. and Nevada, R.,1996. Buildings detection and 
description from monocular aerial images, ARPA Image 
Understanding Workshop, Palm Springs, CA. 
Lu, Y.H., Trinder, J.C. and Kubik, K.,2006. Automatic 
building detection using the Dempster-Shafer algorithm. 
Photogrammetric Engineering and Remote Sensing, 72(4): 
395-403. 
Muller, S. and Zaum, D.,2005. Robust building detection in 
aerial images, CMRT '05, Vienna, pp. 143-148. 
Nevada, R., Lin, C. and Huertas, A., 1997. A system for 
building detection from aerial images. In: A. Gruen, E. 
Baltsavias and O. Henricsson (Editors), Automatic 
extraction of man-made objects from aerial images (II). 
Birkhauser Verlag, Basel, pp. 77-86. 
Rottensteiner, F., Trinder, J., Clode, S. and Kubik, K.,2004a. 
Fusing airborne laser scanner data and aerial imagery for 
the automatic extraction of buildings in densely built-up 
areas, International Archives of Photogrammetry and 
Remote Sensing, Vol. XXXV, Part B3, Istanbul, pp. 512- 
517. 
Rottensteiner, F., Trinder, J., Clode, S., Kubik, K. and Lovell, 
B.,2004b. Building detection by Dempster-Shafer fusion of 
LIDAR data and multispectral aerial imagery, Proceedings 
of the 17th International Conference on Pattern Recognition 
(ICPR’04), Cambridge, United Kingdom. 
Vosselman, G.,1999. Building reconstruction using planar 
faces in very high density height data, ISPRS Conference on 
Automatic Extraction of GIS Objects from Digital Imagery, 
Munich, pp. 87-92. 
Walter, V.,2004. Object-based classification of remote sensing 
data for change detection. ISPRS Journal of 
Photogrammetry and Remote Sensing, 58(2004): 225-238. 
Weidner, U. and Forstner, W.,1995. Towards automatic 
building extraction from high resolution digital elevation 
models. ISPRS Journal of Photogrammetry and Remote 
Sensing, 50(4): 38-49.