A method of land use/land cover change detection from remote sensing image based on support vector machines

Land cover/land use has become one of the crucial but basic tasks in carrying out a series of important work. With the development of remote sensing techniques and Geo analysis model, using remotely sensed data to monitor the status and dynamical change of land cover/land use has become one of the most rapid, credible and effectual approaches. To improve the accuracy of change detection from remote sensing image, this paper introduces a new method of change detection from remote sensing image based on support vector machine (SVM), using multi-spectral remote sensing data. We choose Hengshui city in China as a typical studying sample. The result shows that it is competitive with other recently developed methods for change detection when applied to the same data sets and yield good performance with very limited training data.

[1]  Vladimir N. Vapnik,et al.  The Nature of Statistical Learning Theory , 2000, Statistics for Engineering and Information Science.

[2]  Chunyang He,et al.  The high spatial resolution remote sensing image classification based on SVM with the multi-source data , 2005, Proceedings. 2005 IEEE International Geoscience and Remote Sensing Symposium, 2005. IGARSS '05..

[3]  Joachim M. Buhmann,et al.  Support vector machines for land usage classification in Landsat TM imagery , 1999, IEEE 1999 International Geoscience and Remote Sensing Symposium. IGARSS'99 (Cat. No.99CH36293).

[4]  Ben Gorte,et al.  A method for object-oriented land cover classification combining Landsat TM data and aerial photographs , 2003 .

[5]  Lorenzo Bruzzone,et al.  Classification of hyperspectral remote sensing images with support vector machines , 2004, IEEE Transactions on Geoscience and Remote Sensing.

[6]  J. A. Gualtieri.  Hyperspectral analysis, the support vector machine, and land and benthic habitats , 2003, IEEE Workshop on Advances in Techniques for Analysis of Remotely Sensed Data, 2003.

[7]  Sigeru Omatu,et al.  Extended LVQ Neural Network Approach to Land Cover Mapping , 1999, IEEE Trans. Geosci. Remote. Sens..

[8]  Bernhard E. Boser,et al.  A training algorithm for optimal margin classifiers , 1992, COLT '92.

[9]  Steven A. Sader,et al.  Using Bayesian statistics, Thematic Mapper satellite imagery, and breeding bird survey data to model bird species probability of occurrence in Maine , 1997 .

[10]  Robert F. Cromp,et al.  Support Vector Machine Classifiers as Applied to AVIRIS Data , 1999 .

[11]  W. Deng,et al.  Detecting coal fires with a neural network to reduce the effect of solar radiation on Landsat Thematic Mapper thermal infrared images , 2001 .