**7.1 System evaluation**

For the demonstration of the created system, a scanned point cloud section related to Deutsch Bahn scene in the city of *Nürnberg* was extracted. While the last one measure 87 kms, we have just taken a small scene of 500m. It contains a variety of the target objects. The

From Unstructured 3D Point Clouds to Structured Knowledge - A Semantics Approach 241

The last step consists in annotating the different geometries. Vertical elements with certain characteristics can be annotated directly. Subsequently, further annotation may be relayed on aspects expressing facts to orientation or size of elements, which may be sufficient to finalize a decision upon the semantic of an object or, in more sophisticated cases, our prototype allows the combination of semantic information and topological ones that can deduce more robust results minimizing the false acceptation rate. The extracted scene contains 37 elements. As well, in most cases, our annotation process is able to affect the right label to the detected Bounding box based on knowledge on its component, its internal and external topology where among 13 elements are classified as Masts, three as a SchaltAnlage

Scene Size Detected Bounding Box Annotated elements Truth data

Masts signal Schaltanlage

Scene1 500m 105 34 37

Annotated 13 18 3 Truth data 12 20 5

Table 6. Detected Element within the scene and annotated ones.

Table 7. Detected and annotated elements within the scene1.

Fig. 15. Knowledge base after the annotation process.

and 18 signals, Table 6, Table 7, Fig.15.

Fig. 14. Snapshot of the WiDOP prototype (top), Detected and annotated elements visualization within VRML language (bottom).

whole scene has been scanned using a terrestrial laser scanner fixed within a train, resulting in a large point cloud representing the surfaces of the scene objects. Within the created prototype, different SWRL rules are processed. First, geometrical elements will be searched in the area of interest based on dynamic 3D processing algorithm sequence created depending on semantic object properties. The second step aims to identify existing topologies between the detected geometries. Thus, useful topologies for geometry annotation are tested. Topological Built-Ins like topo:isConnected, topo:touch, topo:Perpendicular, topo:isDistantfrom are created. As a result, relations found between geometric elements are propagated into the ontology, serving as an improved knowledge base for further processing and decision.

240 Semantics – Advances in Theories and Mathematical Models

Fig. 14. Snapshot of the WiDOP prototype (top), Detected and annotated elements

whole scene has been scanned using a terrestrial laser scanner fixed within a train, resulting in a large point cloud representing the surfaces of the scene objects. Within the created prototype, different SWRL rules are processed. First, geometrical elements will be searched in the area of interest based on dynamic 3D processing algorithm sequence created depending on semantic object properties. The second step aims to identify existing topologies between the detected geometries. Thus, useful topologies for geometry annotation are tested. Topological Built-Ins like topo:isConnected, topo:touch, topo:Perpendicular, topo:isDistantfrom are created. As a result, relations found between geometric elements are propagated into the ontology, serving as an improved

visualization within VRML language (bottom).

knowledge base for further processing and decision.

The last step consists in annotating the different geometries. Vertical elements with certain characteristics can be annotated directly. Subsequently, further annotation may be relayed on aspects expressing facts to orientation or size of elements, which may be sufficient to finalize a decision upon the semantic of an object or, in more sophisticated cases, our prototype allows the combination of semantic information and topological ones that can deduce more robust results minimizing the false acceptation rate. The extracted scene contains 37 elements. As well, in most cases, our annotation process is able to affect the right label to the detected Bounding box based on knowledge on its component, its internal and external topology where among 13 elements are classified as Masts, three as a SchaltAnlage and 18 signals, Table 6, Table 7, Fig.15.


Table 6. Detected Element within the scene and annotated ones.


Table 7. Detected and annotated elements within the scene1.

Fig. 15. Knowledge base after the annotation process.

From Unstructured 3D Point Clouds to Structured Knowledge - A Semantics Approach 243

intervene within the detection and annotation process to make the process more flexible and

This paper chapter work performed in the framework of the research project funded by the German ministry of research and education under contract No. 1758X09. The authors

Allemang, D. & Hendler, J A. (2008). *Semantic web for the working ontologist: modeling in RDF, RDFS and OWL,* Morgan Kaufmann, ISBN 9780123735560, Amsterdam. Antoniou, G. & Harmelen, F. Web ontology language: Owl, Handbook on ontologies,

Horrocks, I. Peter, F. Schneider, P. Deborah, L. McGuinness & Christopher, A. (2007). *OWL:* 

Baader, F. *Nonstandard inferences in description logics: The story so far*, Mathematical Problems

Baader, F. Horrocks, I. & Sattler, U. *Description logics*, Foundations of Artificial

Balzani, M. Santopuoli, N. Grieco, A. & Zaltron, N. (2004) Laser Scanner 3D Survey in

Ben Hmida, H. Cruz, C. Nicolle, C. & Boochs, F. (2010). From 3D point clouds to semantic

Ben Hmida, H. Cruz, C. Nicolle, C. & Boochs, F. (2010). Semantic-based Technique for the

Boley, H. Osmun, T M. & Craig, B L. (2009). WellnessRules: A Web 3.0 Case Study in RuleML-Based Prolog, *N3 Profile Interoperation*, Vol. 5858, p 43, 2009. Boochs, F. Marbs, A. Ben Hmida, H. Truong, H. Karmachaiya, A. Cruz, C. Habed, A.

Bosche, F. & Haas, CT. (2008). Automated retrieval of 3D CAD model objects in construction range images *Automation in Construction,* Elsevier, Vol. 17, pp. 499-512, 2008. Calvanese, D. De Giacomo, G. Lembo, D. Lenzerini, M & Rosati, R. (2005).DL-Lite: Tractable

Campbell, RJ. & Flynn, PJ.(2001). A survey of free-form object representation and

recognition techniques, *Computer Vision and Image Understanding*, Vol. 81, pp. 166-

object, *KEOD, theInternational Joint Conference on Knowledge Discovery, Knowledge* 

Automation the 3D Reconstruction Process, *SEMAPRO 2010, The Fourth International Conference on Advances in Semantic Processing*, Florence, Italy, pp. 191-

Nicolle, C. & Voisin, Y. (2010). Integration of knowledge to support automatic object reconstruction from images and 3D data. *International Multi-Conference on* 

*a Description Logic Based Ontology Language for the Semantic Web*, Proc of the 21st Int

intelligent.

**9. Acknowledgment** 

**10. References** 

cordially thank for this funding.

198, 2010.

210, 2001.

Springer, 2009, pp. 91-110.

Conf on Automated Deduction.

from Applied Logic I., Springer, pp. 1-75, 2006.

Intelligence. Elsevier, 2008. Vol. 3. pp. 135-179, 2008.

*Engineering and Knowledge Management,* Paris, 2011.

Berners-Lee, T. (1998). Semantic web road map, 1998.

Archaeological Field, *the Forum Of Pompeii*, pp. 18-21, 2004.

*Systems, Signals & Devices*, Sousse Tunisia : pp. 1-13, 2011.

description logics for ontologies, Vol. 20, p. 602, 2005.

Some limits are detected while making extra tests, especially with the SchaltAnlage object detection where the rate of false detection still high. Before explaining the reason behind this false detection, let's recall that the Schaltanlage present very small electronic boxes installed on the ground. In the some cases, lots of bounding boxes are detected where a high average of them presents small noise on the ground. The reason for the false annotation is the lack of semantic characteristics related to such elements since, until now; there is no real internal or external topology neither internal geometric characteristic that discriminate such an element compared to others.
