Classification of High Resolution Sar Imagery Using Local Indicators of Spatial Association

Abstract:

In this paper, we will propose a novel classification method of high-resolution SAR using local autocorrelation and Support Vector Machines (SVM) classifier. The commonly applied spatial autocorrelation indexes, called Moran's Index; Geary's Index, Getis's Index, will be used to depict the feature of the land-cover. Then, the SVM based on these indexes will be applied as the high-resolution SAR classifier. A Cosmo-SkyMed scene in ChengDu city, China is used for our experiment. It is shown that the method proposed can lead to good classification accuracy.

• Periodical: Applied Mechanics and Materials (Volumes 333-335)
• Pages: 1080-1084
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.333-335.1080
• Online since: July 2013
• Authors: Zhang Fei, Ye Xi
• Keywords: Classification, Cosmo-SkyMed, Local Autocorrelation, Support Vector Machine (SVM)

References

[1] Soe W. Myint et al, Employing Spatial Metrics in Urban Land-use/Land-cover Mapping: Comparing the Getis and Geary Indices, AAG REMOTE SENSING SPECIALITY GROUP (2007).

DOI: 10.14358/pers.73.12.1403

[2] B. Ghimire, et al, Contextual land-cover classification: incorporating spatial dependence in land-cover classification models using random forests and the Getis statistic, Remote Sensing Letters, vol. 1, No. 1, March 2010, p.45–54.

DOI: 10.1080/01431160903252327

[3] Anselin, Local Indicators of Spatial Association, Geographical Analysis, (1995).

[4] M. Stasolla, P. Gamba, Spatial Indexes for the Extraction of Formal and Informal Human Settlements From High-Resolution SAR Images, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, vol. 1, 2008, pp.98-106.

DOI: 10.1109/jstars.2008.921099

[5] A. Roth, TerraSAR-X: a new perspective for scientific use of high resolution spaceborne SAR data, in Proc. 2nd GRSS/ISPRS Joint Workshop on Remote Sensing and Data Fusion over Urban Areas, Berlin, Germany, May 22–23, 2003, p.4–7.

DOI: 10.1109/dfua.2003.1219945

[6] F. Impagnatiello, R. Bertoni, and F. Caltagirone, The SkyMed/COSMO system: SAR payload characteristics, in Proc. IGARSS, Seattle, WA, Jul. 6–10, 1998, vol. 2, p.689–691.

DOI: 10.1109/igarss.1998.699552

[7] U. Benz, M. Baatz, and G. Schreier, OSCAR-object oriented segmentation and classification of advanced radar allow automated information extraction, IEEE International Geoscience and Remote Sensing Symposium, 2001, vol. 4, p.1913-(1915).

DOI: 10.1109/igarss.2001.977114

[8] P. Gamba, et al, Anisotropic Rotation Invariant Built-Up Presence Index: Applications to SAR Data, IEEE International Geoscience and Remote Sensing Symposium, 2008, vol. 5, pp.334-341.

DOI: 10.1109/igarss.2008.4780097

[9] Dengxin, Dai. et al, Multilevel Local Pattern Histogram for SAR Image Classification, IEEE Geoscience and Remote Sensing Letters, vol. 8, 2011, pp.225-229.

DOI: 10.1109/lgrs.2010.2058997