Improving Spatiotemporal Change Detection: A High Level Fusion Approach for Discovering Uncertain Knowledge from Satellite Image Database

Authors: Wadii Boulila, Imed Riadh Farah, Karim Saheb Ettabaa, Basel Solaiman, Henda Ben Ghezala

Abstract:

This paper investigates the problem of tracking spa¬tiotemporal changes of a satellite image through the use of Knowledge Discovery in Database (KDD). The purpose of this study is to help a given user effectively discover interesting knowledge and then build prediction and decision models. Unfortunately, the KDD process for spatiotemporal data is always marked by several types of imperfections. In our paper, we take these imperfections into consideration in order to provide more accurate decisions. To achieve this objective, different KDD methods are used to discover knowledge in satellite image databases. Each method presents a different point of view of spatiotemporal evolution of a query model (which represents an extracted object from a satellite image). In order to combine these methods, we use the evidence fusion theory which considerably improves the spatiotemporal knowledge discovery process and increases our belief in the spatiotemporal model change. Experimental results of satellite images representing the region of Auckland in New Zealand depict the improvement in the overall change detection as compared to using classical methods.

Keywords: Knowledge discovery in satellite databases, knowledge fusion, data imperfection, data mining, spatiotemporal change detection.

Digital Object Identifier (DOI): doi.org/10.5281/zenodo.1082979

References:

[1] Bloch. Fusion d'Informations en Traitement du Signal et des Images. H. Sciences, Ed. Paris, France: Germes Lavoisier, 2003.
[2] W. Boulila, K. S. Ettabaa, I. R. Farah, B. Solaiman, and H. B. Ghezala. Vers un systeme multi-approche d'extraction de connaissances spatio-temporelles incertaines en imagerie satellitaire. SETIT 2009 5th Inter-national Conference: Sciences of Electronic, Technologies of Information and Telecommunications, Tunisie, March 22-26 2009.
[3] M. Chau, R. Cheng, B. Kao, and J. Ng. Uncertain data mining: An example in clustering location data. In the Methodologies for Knowledge Discovery and Data Mining, Pacific Asia Conference PAKDD 2006, Singapore, pages 199-204, April 2006.
[4] P. Clark and T. Niblett. The cn2 induction algorithm. Machine Learning 3, pages 261-283, 1989.
[5] R. 0. Duda and P. E. Hart. Pattern classification and scene analysis. John Wiley and Sons, 1973.
[6] I. R. Farah, W. Boulila, K. S. Ettabaa, and M. B. Ahmed. Multi-approach system based on fusion of multi-spectral images for land cover classification. IEEE Trans. Geosci. Remote Sens., 46(12):4153-4161, December 2008.
[7] I. R. Farah, W. Boulila, K. S. Ettabaa, B. Solaiman, and M. B. Ahmed. Interpretation of multi-sensor remote sensing images: Multi-approach fusion of uncertain information. IEEE Trans. Geosci. Remote Sens., 46(12):4142-4152, December 2008.
[8] U. M. Fayyad, G. Piatetsky-Shapiro, and P. Smyth. From data mining to knowledge discovery: An overview. pages 1-30. Menlo Park, Calif.: AAAI Press, 1996.
[9] F. Gullo, G. Ponti, A. Tagarelli, and S. Greco. A hierarchical algorithm for clustering uncertain data via an information-theoretic approach. In Proceedings of 2008 Eighth IEEE International Conference on Data Mining, pages 821— 826, 2008.
[10] Y. Huang, L. Zhang, and P. Zhang. A framework for mining sequential patterns from spatio-temporal event data sets. IEEE Transactions on Knowledge and data engineering, 20(4):433-448, April 2008.
[11] H. P. Kriegel and M. Pfeifle. Density-based clustering of uncertain data. In Proceedings of the 11th ACM SIGKDD international conference on Knowledge discovery in data mining, Chicago, Illinois, USA, pages 672¬677, 2005.
[12] N. Mamoulis, H. Cao, and G. Kollios. Mining, indexing, and query¬ing historical spatiotemporal data. KDD'04 Knowledge Discovery in Databases, Seattle, Washington, USA, pages 236-245, August 22-25 2004.
[13] J. Quinlan. C4.5: programs for machine learning. Morgan Kaufmann, San Mateo, CA, 1993.
[14] Y. Tao, C. Faloutsos, D. Papadias, and B. Liu. Prediction and indexing of moving objects with unknown motion patterns. SIGMOD 2004, Paris, France, June 13-18 2004.
[15] I. Tsoukatos and D. Gunopulos. Efficient mining of spatiotemporal patterns. Symposium on Advances in Spatial and Temporal Databases, pages 425-442, 2001.
[16] F. Verhein. Mining complex spatio-temporal sequence patterns. In Proceedings of the Ninth SIAM International Conference on Data Mining, John Ascuaga's Nugget, Nevada, April 30-May 2, 2009.