Abstract
Map databases usually suffer from obsolete scene details due to frequently occurring changes, therefore automatic change detection has become vital. Generally, change detection is done by spectral analysis of multi temporal images without including elevation information. In this paper, we describe a method for urban change detection by fusing high resolution aerial images with airborne lidar data which provides elevation information. For dealing with radiometric differences, three supervised learning algorithms are introduced which reduce the need for radiometric corrections. Three experiments are conducted on different training sets for each algorithm, to evaluate their performance on change detection and their sensitivity to unbalanced and noisy datasets. All algorithms are also compared with the standard PCA method. Experimental results demonstrate the capabilities of these methods and a detailed theoretical analysis of the achieved results is also presented.
Access provided by Autonomous University of Puebla. Download to read the full chapter text
Chapter PDF
Similar content being viewed by others
References
Singh, A.: Digital Change Detection Techniques Using Remotely-sensed Data. International Journal of Remote Sensing 10, 989–1004 (1989)
Lu, D., Mausel, P., Brondízio, E., Moran, E.: Change Detection Techniques. International Journal of Remote Sensing 25, 2365–2401 (2004)
Luo, B., Chanussot, J.: Geometrical Features for the Classification of Very High Resolution Multispectral Remote-sensing Images. In: 17th IEEE International Conference on Image Processing, pp. 1045–1048. IEEE Press, Hong Kong (2010)
Trinder, J., Salah, M.: Aerial Images and Lidar Data Fusion for Disaster Change Detection. In: The XXII Congress of the International Society for Photogrammetry and Remote Sensing, Melbourne, pp. 227–232 (2012)
Li, M.C., Cheng, L., Gong, J.Y., Liu, Y.X., Chen, Z.J., Li, F.X., Chen, G., Song, X.G.: Post-earthquake Assessment of Building Damage Degree Using Lidar Data and Imagery. Science in China, Series E: Technological Sciences 51, 133–143 (2008)
Chen, L.C., Lin, L.J.: Detection of Building Changes from Aerial Images and Light Detection and Ranging (LIDAR) Data. Journal of Applied Remote Sensing 4, art. no. 041870 (2010)
Zometzer, S.F., Davis, J.L., Lau, C.: An Introduction to Neural and Electronic Networks, 2nd edn. Academic Press, New York (1994)
Vapnik, V.N.: Universal Learning Technology: Support Vector Machines. NEC Journal of Advanced Technology 2, 137–144 (2005)
Friedman, J., Hastie, T., Tibshirani, R.: Additive Logistic Regression: A Statistical View of Boosting. Annals of Statistics 28, 337–407 (2000)
Ng, W., Dash, M.: An Evaluation of Progressive Sampling for Unbalanced Data Sets. In: 6th IEEE International Conference on Data Mining Workshops, pp. 657–661. IEEE Press, Hong Kong (2006)
LIBSVM: A Library for Support Vector Machines, http://www.csie.ntu.edu.tw/~cjlin/libsvm
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2013 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Zong, K., Sowmya, A., Trinder, J. (2013). Machine Learning Based Urban Change Detection by Fusing High Resolution Aerial Images and Lidar Data. In: Bian, F., Xie, Y., Cui, X., Zeng, Y. (eds) Geo-Informatics in Resource Management and Sustainable Ecosystem. Communications in Computer and Information Science, vol 398. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-45025-9_51
Download citation
DOI: https://doi.org/10.1007/978-3-642-45025-9_51
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-45024-2
Online ISBN: 978-3-642-45025-9
eBook Packages: Computer ScienceComputer Science (R0)