XXIX-B1, 2012
ASM infers the rules
Igorithms. Algorithm
mended, considering
For.Line3D (8)
iplements the same
wledge domains. We
owledge under class
viation of a dataset
ASM then infers the
ning noise. It shows
combining different
to classes of objects,
ASM to interact with
answers for detecting
is necessary to define
of these knowledge
edge schema (fig. 2)
ource. We use a 3D
se, however it is also
S.
rent situations, for
y or data. Even two
might need to be
shown in Equation 6
on3DbyRANSAC for
same parameters for
1 principle, it should
int densities of the
ints within the linear
'adius value for thick
detection
ng and modeling the
1 observation of the
induced in the KB.
ts as they are tested
r characteristics. The
ations for Mast and
n selects a different
"tionin3 DbyRANSA C
iate the rules defined
s for different cases.
.. ASM recommends
he detection process
ig 3D point cloud of
Xf). The KB consists
International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, Volume XXXIX-B1, 2012
XXII ISPRS Congress, 25 August — 01 September 2012, Melbourne, Australia
of the objects found in the scene along with the algorithms that
could possibly be used to detect them.
Table 1 presents the detection and qualification of objects in the
scene through ISCM within the WiDOP platform. There were
105 geometries detected and among them 34 were semantically
annotated. 71 detected geometries are not annotated because the
KB did not contain enough rules to classify them. Although
currently the results are based on unsophisticated data and rule
sets, we believe that those objects would be correctly annotated
after further enrichment of the KB. Mismatches visible from
Table 1 show the necessity of improvements by addition of
modification of rules within the KB. However, results already
show the general functioning of such a flexible approach.
Objects Annotated | Reality
Masts 13 12
Signal 18 20
SwitchGear | 3 5
Table 1. The first set of results
The result seen in table 1 through the knowledge driven method
is satisfactory considering the complexity of the scene. Rule
modifications would improve results, and further development
in this regard is ongoing.
4. CONCLUSIONS
The knowledge driven approach for selecting algorithms
suitable to detect objects has been presented. Building on
previous research, technologies within the Semantic Web have
been advanced, and SWRL in particular has been extended in
the qualification process. Keeping the essence of the knowledge
based approach in processing, this solution uses a methodology
that fuses knowledge from different knowledge domains for
suitable algorithmic selection, which leads to a flexible
processing chain for detecting objects. Furthermore, the
integration of simulation knowledge, representing behavioral
knowledge of algorithms in different situations and patterns,
adds more flexibility.
5. ACKNOWLEDGEMENTS
This paper presents work performed in the framework of a
research project funded by the German ministry of research and
education under contract No. 1758X09. We also acknowledge
the contributions from Helmi Ben Hmida, Hung Quoc Truong,
Christophe Cruz and Adlane Habed.
References
Anguelov, D., Taskarf, B., Chatalbasev, V., Koller, D., Gupta, D., & Ng,
A., 2005. Discriminative learning of Markov random fields for
segmentation of 3D scan data . In: Conference on Computer Vision and
Pattern Recognition, 2005. CVPR 2005. IEEE Computer Society, San
Diego, USA, IEBExplore, pp. 169 -176.
Bechhofer, S., Harmelen, F. v., Hendler, J., Horrocks, I., McGuinness,
D. L., Patel-Schneider, P. E., & Stein, L. A., 2004. ,OWL Web Ontology
Language”, from W3C Recommendation: http://www.w3.org/TR/owl-
ref/ (28 Nov 2010)
95
Beker, S., 2009. Generation and application of rules for quality
dependent facade reconstruction. In: ISPRS Journal of Photogrammetry
and Remote Sensing, pp. 640 - 653.
Ben Hmida, H., Cruz, C., Nicolle, C., & Boochs, F., 2011. Toward the
Automatic Generation of a Semantic VRML Model from Unorganized
3D Point Clouds. In: The Fifth International Conference on Advances
in Semantic Processing. Lisbon Portugal.
Berners-Lee, T., 1998. “Why RDF model is different from the XML
model.", from W3C: A roadmap to the Semantic Web.
http://www.w3.org/DesignIssues/Overview.html (22 Oct 2010).
Frueh, C., Jain, S., & Zakhor, A., 2002. Data processing algorithms for
generating textured 3D building facade meshes from laser scans and
camera images. Interantion Journal for Computer Vision, pp. 834 - 847.
Golovinskiy, A., Kim, G. V., & Funkhouser, T., 2009. Shape-based
Recognition of 3D Point Clouds in Urban Environment. In:
International Conference on Computer Vision (ICCV), Kyoto, Japan
IEEExplore, pp. 2154 - 2161.
Horrocks, I., Schneider, P. f., Boley, H., Tabelt, S., Grosof, B., & Dean,
M., 2004. “SWRL - A Semantic Web Rule Language - Combining
OWL and RuleML", SWRL: A Semantic Web Rule Language -
Combining OWL and RuleML.
http://www.w3.org/Submission/SWRL/ (22 May 2009)
Koppula, S. H., Anand, A., Joachims, T., & Saxena, A., 2011. Semantic
Labeling of 3D Point Clouds for Indoor Scenes. In: Twenty-Fifth
Annual Conference on Neural Information Processing Systems.
Granada, Spain.
Maillot, E, N., Thonnat M., 2008. Ontology based complex object
recognition. In. Image and Vision Computing. Vol. 26 Issue 1,
Butterworth-Heinmann Newton, MA, pp. 102 - 113
Munoz, D., Vandapel, N., & Hebert, M., 2009. Onboard contextual
classification of 3-d point clouds with learned high-order Markov
random fields. In: Proceedings of the 2009 IEEE international
conference on Robotics and Automation, IEEE Press, Kobe, Japan , pp.
4273 - 4280.
Patel-Schneider, P. F., Hayes, P., & Horrocks, I., 2004. “OWL Web
Ontology Language”, W3C Recommendation:
http://www.w3.org/TR/owl-semantics/ (12 July 2010)
Pu, S., 2010. Knowledge based building facade reconstruction from
laser point clouds and images. Twente: Optima Grafische
Communicatie B.V.
Ripperda, N., 2008. Grammer based facade reconstruction using
RjMCMC. In: Photogrammetrie Fernerkundung Geoinformation.
Shapovalov, R., Velizhev, A., & Barinova, O., 2010. Non-associative
markov networks for 3d point cloud Classification. In:
Photogrammetric Computer Vision and Image Analysis - ISPRS
Commission III symposium, Paris, France, PCV 2010, pp. 103 -108.
W3C. (1995, April 17). VRML Virtual Reality Modeling Language.
Retrieved December 18, 2011, from
http://www.w3.org/MarkUp/VRML/
Wessel, R., Wahl, R., Klein, R., & Schnabel, R. (2008). Shape
recognition in 3D point clouds. The 16-th International Conference in
Central Europe on Computer Graphics, Visualization and Computer
Vision. Plzen - Bory: UNION Agency-Science Press.
