The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences. Vol. XXXVII. Part B5. Beijing 2008 
While the overall segmentation features improvement to the 
basic ones, both features suggest that the segmentation along the 
proposed scheme can be further pursued in several directions. 
These include inclusion of additional cues that may feature 
other elements characterizing natural scenes, introducing 
merging schemes for segments based on connectivity and forms 
of similarity, and the analysis of occlusions as a means merge 
disconnected segments that belong in fact to the same object. 
4. CONCLUDING REMARKS 
The paper proposed an approach for the segmentation of 
terrestrial laser point clouds while assembling and integrating 
different data sources. The proposed model offers a general 
framework in the sense that it can utilize different features and 
can be customized according to application requirements. 
Overall, the results show that integration of different cues and 
information sources into a laser scanning segmentation has 
managed providing improved results in relation to each of the 
individual channels. 
The model demonstrated that using an intuitive scheme for 
selecting the best segments from different segmentation maps 
provides satisfactory results. The solution for weighting the 
importance of different cues to the overall segmentation is 
modeled as a crisp decision favoring dominant segments in 
object space as long as they do not violate preset rules. Future 
work in this regards will pursue alternative weighting schemes 
for the data arriving from the individual channels. 
ACKNWOLEDGEMENT 
The authors would like to thank Dr. Claus Brenner for making 
the data used for our tests available. 
REFERENCES 
Alpert S., Galun M., Basri R., Brandt A., 2007. Image 
segmentation by probabilistic bottom-up aggregation and cue 
integration. IEEE Conference on Computer Vision and Pattern 
Recognition (CVPR). Minneapolis, June 2007. 
Bleyer, M., and Gelautz, M., 2004. A layered stereo algorithm 
using image segmentation and global visibility constraints, in 
Proc. of ICIP 2004 5: 2997-3000. 
Brandt A., 1986. Algebraic multigrid theory: the symmetric 
case. Appl. Math. Comput, 19 pp. 23-56. 
Carson, C. Belongie, S. Greenspan, H. Malik, J. 2002. 
Blobworld: image segmentation using expectation- 
maximization and its application to image querying. IEEE 
Transactions on Pattern Analysis and Machine Intelligence 
24(8): 1026- 1038. 
Coiras, E., Santamaria, J., Miravet, C., 2000. Segment-based 
registration technique for visual-infrared images. Optical 
Engineering 39(1) pp. 282-289. 
Comaniciu D., Meer. P., 2002. Mean shift: A robust approach 
toward feature space analysis. IEEE transactions on PAMI, 
24:603-19. 
Dold, C., Brenner, C., 2006. Registration of Terrestrial Laser 
Scanning Data using Planar Patches and Image Data, in: H.-G. 
Maas, D. Schneider (Eds.), ISPRS Comm. V, IAPRS Vol. 
XXXVI Part. 5 pp. 78-83. 
Estrada F. J., Jepson A. D., 2005. Quantitative Evaluation of a 
Novel Image Segmentation Algorithm. CVPR (2) 2005: 1132- 
1139. 
Felzenszwalb, P.F., Huttenlocher, D.P., 2004. Efficient Graph- 
Based Image Segmentation, International journal of computer 
vision 59(2) pp. 167-181. 
Gorte B. 2007. Planar feature extraction in terrestrial laser scans 
using gradient based range image segmentation, ISPRS 
Workshop on Laser Scanning, pp. 173-177. 
Hartley R., Zisserman A., 2003. Multiple View Geometry in 
Computer Vision. Cambridge University Press, Second Edition. 
Huang, Q., Wen G., Wenjian C. 2005 Thresholding technique 
with adaptive window selection for uneven lighting image. 
Pattern Recognition Letters 26 pp. 801-808. 
Klaus A., Sormann M., and Kamer K., 2006 Segment-based 
stereo matching using belief propagation and a self-adapting 
dissimilarity measure, in Proc. of ICPR 2006, pp. 15-18. 
Mian, A., Bennamoun, M., Owens, R., 2006. Three- 
Dimensional Model-Based Object Recognition and 
Segmentation in Cluttered Scenes. IEEE transactions on PAMI. 
28(10), 1584-1601. 
Otsu N. 1979. A threshold selection method from gray-level 
histograms. IEEE Trans. Sys., Man., Cyber. 9: 62-66. 
Pal N. R. and Pal S. K., 1993. "A review on image segmentation 
techniques," Pattern Recognition, 26(9): 1277-1294, 1993. 
Rabanni T., 2006. Automatic reconstruction of Industrial 
Installations using point clouds and images. PhD thesis. NCG, 
publication on Geodesy 62. 
Roth, V., Ommer, B., 2006. Exploiting Low-Level Image 
Segmentation for Object Recognition, DAGM06 pp. 11-20. 
Russell, C. B., Efros A., Sivic J., Freeman T. W., Zisserman 
A., 2006. Using Multiple Segmentations to Discover Objects 
and their Extent in Image Collections, in Proc. of CVPR 2006 2, 
1605-1614. 
Sharon E., Brandt A., Basri R., 2000. Fast Multiscale Image 
Segmentation. CVPR 2000: 1070-1077. 
Shi J., Malik J., 2000. Normalized Cuts and Image 
Segmentation. IEEE transactions on PAMI. 22(8): 888-905. 
Vosselman G., S. Dijkman, 2001. 3D Building model 
reconstruction from point clouds and ground plans. IAPRS 
34(3/W4).