Home   >   CSC-OpenAccess Library   >    Manuscript Information
Research on Image Classification Model of Probability Fusion Spectrum-Spatial Characteristics Based on Support Vector Machine
Zheng Zhang, Xiaobing Huang, Hui Li
Pages - 103 - 115     |    Revised - 10-05-2014     |    Published - 01-06-2014
Volume - 8   Issue - 3    |    Publication Date - June 2014  Table of Contents
High Spatial Solution, Spectral - Space Characteristics, Multi-Scale Morphological Sequence, SVM.
For insufficient information of imaging spectrum with high spatial resolution, detailed imaging information, reduction of mixed pixels, increase of pure pixels and problems of image characteristic extraction and model classification produced from this, we provide a classifier model of a united spectrum-spatial multi-characteristic based on SVM, and use this model to finish the image classification. The model completely uses the multi-characteristic information, and overcomes the over-fitting problems produced by accumulating high-dimensional characteristics. The model includes three classifications of spectrum-spatial characteristics, namely spectral characteristics-spectral characteristic of multi-scale morphology, spectral characteristics-physical characteristics of underlaying surfaces of multi-scale morphology and spectral characteristics-features spatial extension characteristics of multi-scale morphology. Firstly the three classifications of spectrum-spatial characteristics are classified through SVM, then carries out the probability fusion for the classification results based on the pixels to obtain the final image classification results. This article respectively uses WorldView-2 image and ROSIS image to experiment, and the results show that the model has better classification effect compared with VS-SVM algorithm.
1 Google Scholar 
2 CiteSeerX 
3 refSeek 
4 Scribd 
5 SlideShare 
6 PdfSR 
Benediktsson J. A., Palmason J. A., Sveinsson J. R..”Classification of hyperspectral data from urban areas based on extended morphological profiles.” Geoscience and Remote Sensing,vol. 43, pp. 480-491, Mar. 2005.
Changshan Wu, Alan T. Murray.”Estimating impervious surface distribution by spectral mixture analysis.” Remote Sensing of Environment, vol. 84, pp. 493–505, Apr. 2003.
Dell'Acqua F., Gamba P., Ferrari A., et al.“Exploiting spectral and spatial information in hyperspectral urban data with high resolution.” Geoscience and Remote Sensing Letters,vol. 1, pp. 322-326, Oct. 2004.
Fauvel M., Benediktsson J. A., Chanussot J., et al.”Spectral and spatial classification of hyperspectral data using SVMs and morphological profiles.” Geoscience and Remote Sensing, vol. 46, pp. 3804-3814, Nov. 2008.
Gamba P., F. Dell’Acqua, G. Lisini, and G. Trianni. “Improved VHR urban mapping exploiting feature boundaries.” Geoscience and Remote Sensing, vol. 45, pp. 2676–2682, Aug. 2007.
Huang X., Zhang L., Li P..“An adaptive multiscale information fusion approach for feature extraction and classification of IKONOS multispectral imagery over urban areas.”Geoscience and Remote Sensing Letters, vol. 4, pp. 654-658, Oct. 2007.
Huang X., Zhang L., Li P..”Classification and Extraction of Spatial Features in Urban Areas Using High Resolution Multispectral Imagery.” Geoscience and Remote Sensing, vol. 4,pp.260–264, Apr. 2007.
Huang X., Zhang L..” A comparative study of spatial approaches for urban mapping using hyperspectral ROSIS images over Pavia City, northern Italy.” International Journal of Remote Sensing, vol. 30, pp. 3205-3221, Jun. 2009.
Huang X., Zhang L..”Morphological Building/Shadow Index for Building Extraction From HighResolution Imagery Over Urban Areas.” Selected Topics in Applied Earth Observations and Remote Sensing, vol. 5, pp. 161–172, Feb. 2012.
Ouma Y. O., Ngigi T. G., Tateishi R..”On the Optimization and Selection of Wavelet Texture for Feature Extraction from High-resolution Satellite Imagery with Application towards Urbantree Delineation.” International Journal of Remote Sensing, vol. 27, pp. 73–104, Feb. 2007.
Pal M., Foody G. M.. “Feature selection for classification of hyperspectral data by SVM.”Geoscience and Remote Sensing, vol. 48, pp. 2297-2307, May 2010.
Pesaresi M., Benediktsson J. A..”A New Approach for The Morphological Segmentation of High-resolution Satellite Imagery.” Geoscience and Remote Sensing, vol. 39, pp. 309–320,Feb 2001.
Ridd, M. K.”Exploring a V–I–S (vegetation–impervious surface–soil) model for urban ecosystem analysis through remote sensing: comparative anatomy for cities.” International Journal of Remote Sensing, vol. 16, pp. 2165–2185, Jan. 1995.
Soille P., Pesaresi M..”Advances in Mathematical Morphology Applied to Geoscience and Remote Sensing.” Geoscience and Remote Sensing, vol. 40, pp. 2042–2055, Sep. 2002.
Tian J., Chen D. M..”Optimization in Multi-scale Segmentation of High-resolution Satellite Images for Artificial Feature Recognition.” International Journal of Remote Sensing, vol. 28,pp. 4625–4644, Sep. 2007.
Waske B, van der Linden S, Benediktsson J A, et al. “Sensitivity of support vector machines to random feature selection in classification of hyperspectral data.” Geoscience and Remote Sensing, vol. 48, pp. 2880-2889, Jul. 2010.
Waske B., Benediktsson J. A.. ”Fusion of support vector machines for classification of multisensor data.” Geoscience and Remote Sensing, vol. 45, pp. 3858-3866, Dec. 2007.
X. Jin, Davis C. H..”Automated Building Extraction from High-resolution Satellite Imagery in Urban Areas Using Structural, Contextual, and Spectral Information” EURASIP Journal on Applied Signal Processing, vol. 2005, pp. 2196–2206, Jan. 2005.
Miss Zheng Zhang
Xi'an University of Science and Technology - China
Mr. Xiaobing Huang
Xi'an University of Science and Technology - China
Professor Hui Li
Aerial remote sensing department The Third Surveying and Mapping Institute of GuiZh ou Province Guiyang, 550004 - China

View all special issues >>