Urban ontology for semantic interpretation of multi-source images

The multiplication of High or Very High Resolution (spatial and spectral) remotely sensed images is an opportunity to characterize and identify urban objects. Image analyses methods using object-oriented approaches, based on the use of domain knowledge, are necessary to classify these data. A major issue in these approaches is domain knowledge formalization and exploitation. In this paper, we present a methodology to build an urban ontology adapted to the multi-level interpretation of multi-source images. Domain knowledge is stored independently in the urban ontology which contains a set of pre-defined terms characterizing urban domain concepts. The ontology is then used in a classification method in order to assign segmented regions into semantic objects. A matching process between the regions and the concepts of the ontology is proposed. The method is tested on Very High Resolution images (0.7m) on the urban area of Strasbourg (France).

[1]  R. Billen,et al.  Establishment of a geographic data dictionary: a case study of UrbIS 2©, the Brussels regional government GIS , 2002 .

[2]  Angela Schwering,et al.  Measuring Semantic Similarity Between Geospatial Conceptual Regions , 2005, GeoS.

[3]  Thomas R. Gruber,et al.  Toward principles for the design of ontologies used for knowledge sharing? , 1995, Int. J. Hum. Comput. Stud..

[4]  Bruce A. Draper,et al.  The schema system , 1988, International Journal of Computer Vision.

[5]  Eero Hyvönen,et al.  Ontology-Based Image Retrieval , 2003, WWW.

[6]  George A. Miller,et al.  WordNet: A Lexical Database for English , 1995, HLT.

[7]  Atilla Baskurt,et al.  Image understanding and scene models: a generic framework integrating domain knowledge and Gestalt theory , 2004, 2004 International Conference on Image Processing, 2004. ICIP '04..

[8]  Anne Puissant,et al.  Télédétection urbaine et résolution spatiale optimale. Intérêt pour les utilisateurs et aide pour les classifications , 2004, Rev. Int. Géomatique.

[9]  A. Puissant,et al.  Deriving Classification Rules from Multiple Remotely Sensed Data with Data Mining. , 2006 .

[10]  Monique Thonnat,et al.  Ontology based object learning and recognition: application to image retrieval , 2004, 16th IEEE International Conference on Tools with Artificial Intelligence.

[11]  Ioannis Kompatsiaris,et al.  A Genetic Algorithm Approach to Ontology-driven Semantic Image Analysis , 2006 .

[12]  M. Berthod,et al.  Automatic classification of planktonic foraminifera by a knowledge-based system , 1994, Proceedings of the Tenth Conference on Artificial Intelligence for Applications.

[13]  Monika Sester,et al.  Knowledge acquisition for the automatic interpretation of spatial data , 2000, Int. J. Geogr. Inf. Sci..

[14]  Marvin Minsky,et al.  A framework for representing knowledge" in the psychology of computer vision , 1975 .

[15]  Bob J. Wielinga,et al.  Ontology-Based Photo Annotation , 2001, IEEE Intell. Syst..

[16]  Richard Lepage,et al.  Knowledge-Based Image Understanding Systems: A Survey , 1997, Comput. Vis. Image Underst..

[17]  U. Benz,et al.  Multi-resolution, object-oriented fuzzy analysis of remote sensing data for GIS-ready information , 2004 .

[18]  Marcel Worring,et al.  Content-Based Image Retrieval at the End of the Early Years , 2000, IEEE Trans. Pattern Anal. Mach. Intell..

[19]  Max J. Egenhofer,et al.  Determining Semantic Similarity among Entity Classes from Different Ontologies , 2003, IEEE Trans. Knowl. Data Eng..

[20]  S. Lefevre,et al.  Watershed Segmentation of Remotely Sensed Images Based on a Supervised Fuzzy Pixel Classification , 2006, 2006 IEEE International Symposium on Geoscience and Remote Sensing.

[21]  Takashi Matsuyama,et al.  SIGMA: A Knowledge-Based Aerial Image Understanding System , 1990 .

[22]  Mark A. Musen,et al.  The Knowledge Model of Protégé-2000: Combining Interoperability and Flexibility , 2000, EKAW.

[23]  Latifur Khan,et al.  Image classification using neural networks and ontologies , 2002, Proceedings. 13th International Workshop on Database and Expert Systems Applications.

[24]  A. Tversky.  Features of Similarity , 1977 .

[25]  Fabien L. Gandon,et al.  Distributed Artificial Intelligence for Distributed Corporate Knowledge Management , 2002, CIA.

[26]  Timothy W. Finin,et al.  Experiments on using Yahoo! categories to describe documents , 1999, Intelligent Information Integration.

[27]  Olga Marino Drews.  Raisonnement classificatoire dans une représentation à objets multi-points de vue. (Classification reasoning in an object oriented multiple viewpoints representation) , 1993 .

[28]  Emmanuel P. Baltsavias,et al.  Object extraction and revision by image analysis using existing geodata and knowledge: current status and steps towards operational systems☆ , 2004 .

[29]  Martin L. King,et al.  Towards a Methodology for Building Ontologies , 1995 .

[30]  A. Puissant,et al.  Vers une démarche orientée-objets pour extraire les objets urbains sur des images THR , 2003 .

[31]  Timothy W. Finin,et al.  Yahoo! as an ontology: using Yahoo! categories to describe documents , 1999, CIKM '99.

[32]  Catherine Roussey,et al.  Une mthode d'indexation smantique adapte aux corpus multilingues , 2001 .

[33]  George A. Miller,et al.  Nouns in WordNet: A Lexical Inheritance System , 1990 .

[34]  M. Herold,et al.  Object-oriented mapping and analysis of urban land use / cover using IKONOS data , 2002 .

[35]  Michael G. Strintzis,et al.  Knowledge-assisted semantic video object detection , 2005, IEEE Transactions on Circuits and Systems for Video Technology.

[36]  The use of " image " in Geographical Information Market : results of an inquiry on the needs of end-users in urban studies , 2001 .

[37]  Marvin Minsky,et al.  A framework for representing knowledge , 1974 .

[38]  Thierry Ranchin,et al.  Fusion of quickbird MS and Pan Data for urban studies , 2003 .