International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, Volume XXXIX-B3, 2012
XXII ISPRS Congress, 25 August — 01 September 2012, Melbourne, Australia
These preliminary results indicate that the proposed scheme can
be used to obtain structure lines without threshold selection that
include the segmentation results.
Future works will focus on the improvement of TEA for corners
and the development of further applications. The evaluation
will be also enhanced to compare with manually edited models
obtained from stereo aerial imagery. In the photogrammetric
perspective, these detected three-dimensional structure lines can
provide initial building information for the development of data
registration and building reconstruction.
5. ACKNOWLEDGEMENT
This study was partially supported by the National Science
Council, Taiwan, under project number 99-2221-E-008-079-
MY3. The FLIMAP LIDAR data was kindly provided by the
faculty of ITC, University of Twente, the Netherlands. The
octree-based split-and-merge segmentation algorithm was
developed by Professor Tseng and Dr. Wang at the National
Cheng Kung University, Taiwan.
References
Ackermann, F., 1999. Airborne laser scanning— present status
and future expectations. ISPRS Journal of Photogrammetry and
Remote Sensing, 54, pp. 64-67.
Cho, W., Jwa, Y.S., Chang, H.J., and Lee, S.H., 2004. Pseudo-
grid based building extraction using airborne lidar data. In:
International Archives of the Photogrammetry and Remote
Sensing, Istanbul, Turkey, Vol. XXXV, Part B3, pp. 378-383.
Fischler, M.A., and Bolles, R.C., 1981. Random sample
consensus: a paradigm for model fitting with applications to
image analysis and automated cartography. Communications of
the ACM, 24(6), pp. 381—395.
Kim, K.H., and Shan J., 2011. Building roof modeling from
airborne laser scanning data based on level set approach. /SPRS
Journal of Photogrammetry and Remote Sensing, 66, pp. 484—
497.
Lo, C.Y., and Chen, L.C., 2011. Building Boundary Detection
Using Topological Gradient Analysis. Proceedings of the 32th
Asian Conference on Remote Sensing, Oct. 3-7, Taipei, Taiwan,
CD-ROM.
Maas, H.G., and Vosselman, G., 1999. Two algorithms for
extracting building models from raw laser altimetry data. /SPRS
Journal of Photogrammetry and Remote Sensing, 54, pp. 153—
163.
Pu, S., and Vosselman, G., 2009. Knowledge based
reconstruction of building models from terrestrial laser scanning
data. ISPRS Journal of Photogrammetry and Remote Sensing,
64, pp. 575-584.
Rau, J.Y., and Lin, B.C., 2011. Automatic roof model
reconstruction from ALS data and 2D ground plans based on
side projection and the TMR algorithm. ISPRS Journal of
Photogrammetry and Remote Sensing, 66, pp. S13-S27.
Sohn, G., and Dowman, I., 2007. Data fusion of high-resolution
satellite imagery and LiDAR data for automatic building
extraction. /SPRS Journal of Photogrammetry and Remote
Sensing, 62, pp. 43-63.
Vosselman, G., and Dijkman, S, 2001. 3D building model
reconstruction from point clouds and ground plans. In:
International Archives of the Photogrammetry and Remote
Sensing, Annapolis, MA, USA, Vol. XXXIV, 3/W4, pp. 37-44,.
144
Wang, M., and Tseng, Y.-H., 2010. Incremental segmentation
of lidar pointclouds with an octree-structured voxelspace. The
Photogrammetric Record, 26(133), pp. 32-57.
Intern
KEY W
ABSTR.
In this x
nbtained
structure
3D point
segment
We dem
of noise.
The deri
active re
geoinfor
Huang e
els is fo
matic ob
potat ck
city mu
trial and
ard very
reconstr
et al, 21
Frahm e
rot |
Since qx
images.
clouds.
planar aj
by mean
further |
Nevatla,
repetitiv
models
meshes
meonstr
gabytes
ities. C
few plar
The rec
either d
shape o
lation tc
nr on th
conical
find cub
cuboid,
cubs
of detac