A shape–size index extraction for classification of high resolution multispectral satellite images

We propose a new spatial feature extraction method for supervised classification of satellite images with high spatial resolution. The proposed shape–size index (SSI) feature combines homogeneous areas using spectral similarity between one central pixel and its neighbouring pixels. A spatial index considers the shape and size of the homogeneous area, and suitable spatial features are parametrically selected. The generated SSI feature is integrated with the original high resolution multispectral bands to improve the overall classification accuracy. A support vector machine (SVM) is employed as a classifier. In order to evaluate the proposed feature extraction method, KOMPSAT-2 (Korea Multipurpose Satellite 2), QuickBird-2 and IKONOS-2 high resolution satellite images are used. The experiments show that the SSI algorithm leads to a notable increase in classification accuracy over the grey level co-occurrence matrix (GLCM) and pixel shape index (PSI) algorithms, and an increase when compared with using multispectral bands only.

[1]  Liang-pei Zhang,et al.  Classification of Very High Spatial Resolution Imagery Based on the Fusion of Edge and Multispectral Information , 2008 .

[2]  Federico Girosi,et al.  An improved training algorithm for support vector machines , 1997, Neural Networks for Signal Processing VII. Proceedings of the 1997 IEEE Signal Processing Society Workshop.

[3]  Liangpei Zhang,et al.  Classification and Extraction of Spatial Features in Urban Areas Using High-Resolution Multispectral Imagery , 2007, IEEE Geoscience and Remote Sensing Letters.

[4]  John B. Kyalo Kiema,et al.  Texture analysis and data fusion in the extraction of topographic objects from satellite imagery , 2002 .

[5]  Curt H. Davis,et al.  A hierarchical fuzzy classification approach for high-resolution multispectral data over urban areas , 2003, IEEE Trans. Geosci. Remote. Sens..

[6]  Jon Atli Benediktsson,et al.  Classification and feature extraction for remote sensing images from urban areas based on morphological transformations , 2003, IEEE Trans. Geosci. Remote. Sens..

[7]  Anne Puissant,et al.  The utility of texture analysis to improve per‐pixel classification for high to very high spatial resolution imagery , 2005 .

[8]  F. Parmiggiani,et al.  An investigation of the textural characteristics associated with gray level cooccurrence matrix statistical parameters , 1995, IEEE Transactions on Geoscience and Remote Sensing.

[9]  Robert M. Haralick,et al.  Textural Features for Image Classification , 1973, IEEE Trans. Syst. Man Cybern..

[10]  Yun Zhang,et al.  Optimisation of building detection in satellite images by combining multispectral classification and texture filtering , 1999 .

[11]  Jon Atli Benediktsson,et al.  Classification of remote sensing images from urban areas using a fuzzy possibilistic model , 2006, IEEE Geoscience and Remote Sensing Letters.

[12]  Y. Ouma,et al.  Analysis of co‐occurrence and discrete wavelet transform textures for differentiation of forest and non‐forest vegetation in very‐high‐resolution optical‐sensor imagery , 2008 .

[13]  Pakorn Watanachaturaporn.  Classification of remote sensing images using support vector machines , 2005 .

[14]  P. Atkinson,et al.  Fine spatial resolution satellite sensors for the next decade , 1997 .

[15]  Li-hua Xia,et al.  Technical Note. A method to improve classification with shape information , 1996 .

[16]  Peng Gong.  Reducing boundary effects in a kernel-based classifier , 1994 .

[17]  Dongmei Chen,et al.  Examining the effect of spatial resolution and texture window size on classification accuracy: an urban environment case , 2004 .

[18]  Jon Atli Benediktsson,et al.  Exploiting spectral and spatial information in hyperspectral urban data with high resolution , 2004, IEEE Geoscience and Remote Sensing Letters.

[19]  Ron Kohavi,et al.  A Study of Cross-Validation and Bootstrap for Accuracy Estimation and Model Selection , 1995, IJCAI.

[20]  Liangpei Zhang,et al.  A pixel shape index coupled with spectral information for classification of high spatial resolution remotely sensed imagery , 2006, IEEE Transactions on Geoscience and Remote Sensing.

[21]  Pierre Soille,et al.  Beyond self-duality in morphological image analysis , 2005, Image Vis. Comput..

[22]  Chih-Jen Lin,et al.  Probability Estimates for Multi-class Classification by Pairwise Coupling , 2003, J. Mach. Learn. Res..

[23]  M. A. Shaban,et al.  Evaluation of merging SPOT multispectral and panchromatic data for classification of urban environment , 1999, IEEE 1999 International Geoscience and Remote Sensing Symposium. IGARSS'99 (Cat. No.99CH36293).

[24]  P. Gong,et al.  Object-based Detailed Vegetation Classification with Airborne High Spatial Resolution Remote Sensing Imagery , 2006 .

[25]  N. Lam,et al.  Wavelets for Urban Spatial Feature Discrimination: Comparisons with Fractal, Spatial Autocorrelation, and Spatial Co-Occurrence Approaches , 2004 .

[26]  M. Hodgson.  What Size Window for Image Classification? A Cognitive Perspective , 1998 .

[27]  William J. Emery,et al.  A neural network approach using multi-scale textural metrics from very high-resolution panchromatic imagery for urban land-use classification , 2009 .

[28]  Peijun Li,et al.  Multivariate Image Texture by Multivariate Variogram for Multispectral Image Classification , 2009 .

[29]  Curt H. Davis,et al.  A combined fuzzy pixel-based and object-based approach for classification of high-resolution multispectral data over urban areas , 2003, IEEE Trans. Geosci. Remote. Sens..