Spatial location and ecological content of support vectors in an SVM classification of tropical vegetation

The Support Vector Machines (SVM) are increasingly far-reaching in remotely sensed data classification. As supervised classifiers, the SVM output depends on the input pixels, pointing out that training is potentially an important stage for optimizing classification accuracy. The SVM consist in projecting pixels into a high-dimensional feature space and then fitting in a hyperplane, maximizing the distance between the closest vectors and the hyperplane itself. This study aims to locate the pixels acting as support vectors and identify the ecological features they contain in a tropical vegetation context. The analyses focused on a Quickbird-2 image where two vegetation types occur. The physical boundary between classes was delineated in the field, and we used an iterative method to mark and localize the pixels acting as support vectors on the image. Our results highlight that vegetation sampling should focus on ecotones (the transition area between two different and adjacent vegetation classes) in order to minimize the field survey effort and maximize the mapping accuracy.

[1]  Giles M. Foody,et al.  A relative evaluation of multiclass image classification by support vector machines , 2004, IEEE Transactions on Geoscience and Remote Sensing.

[2]  J. Townshend,et al.  Beware of per-pixel characterization of land cover , 2000 .

[3]  Chih-Jen Lin,et al.  LIBSVM: A library for support vector machines , 2011, TIST.

[4]  Ludovic Roux,et al.  Characterisation of ecotones using membership degrees computed with a fuzzy classifier , 1998 .

[5]  Paul M. Mather,et al.  Support vector machines for classification in remote sensing , 2005 .

[6]  Jon Atli Benediktsson,et al.  Neural Network Approaches Versus Statistical Methods in Classification of Multisource Remote Sensing Data , 1989, 12th Canadian Symposium on Remote Sensing Geoscience and Remote Sensing Symposium,.

[7]  J. Lesparre,et al.  USING MIXED PIXELS FOR THE TRAINING OF A MAXIMUM LIKELIHOOD CLASSIFICATION , 2006 .

[8]  Paul M. Mather,et al.  Some issues in the classification of DAIS hyperspectral data , 2006 .

[9]  Lorenzo Bruzzone,et al.  Classification of hyperspectral remote-sensing data with primal SVM for small-sized training dataset problem☆ , 2008 .

[10]  Jungho Im,et al.  ISPRS Journal of Photogrammetry and Remote Sensing , 2022 .

[11]  G. Salvucci,et al.  Eagleson’s optimality theory of an ecohydrological equilibrium: quo vadis? , 1997 .

[12]  Giles M. Foody,et al.  The use of small training sets containing mixed pixels for accurate hard image classification: Training on mixed spectral responses for classification by a SVM , 2006 .

[13]  Giles M. Foody,et al.  An overview of recent remote sensing and GIS based research in ecological informatics , 2011, Ecol. Informatics.

[14]  L. S. Davis,et al.  An assessment of support vector machines for land cover classi(cid:142) cation , 2002 .

[15]  Juan J. Flores,et al.  The application of artificial neural networks to the analysis of remotely sensed data , 2008 .

[16]  Gabriele Moser,et al.  Partially Supervised classification of remote sensing images through SVM-based probability density estimation , 2005, IEEE Transactions on Geoscience and Remote Sensing.

[17]  Chih-Jen Lin,et al.  A Practical Guide to Support Vector Classication , 2008 .

[18]  Classification of Land Cover Using Decision Trees and Multiple Reference Data Sources , 2005 .

[19]  B. Lang,et al.  Efficient optimization of support vector machine learning parameters for unbalanced datasets , 2006 .

[20]  Giles M. Foody,et al.  Crop classification by support vector machine with intelligently selected training data for an operational application , 2008 .

[21]  Luis Alonso,et al.  Robust support vector method for hyperspectral data classification and knowledge discovery , 2004, IEEE Transactions on Geoscience and Remote Sensing.

[22]  M. Fladeland,et al.  Remote sensing for biodiversity science and conservation , 2003 .