Crop classification by a support vector machine with intelligently selected training data for an operational application

摘要

The accuracy of supervised classification is dependent to a large extent on the training data used. The aim is often to capture a large training set to fully describe the classes spectrally, commonly with the requirements of a conventional statistical classifier in-mind. However, it is not always necessary to provide a complete description of the classes, especially if using a support vector machine (SVM) as the classifier. A SVM seeks to fit an optimal hyperplane between the classes and uses only some of the training samples that lie at the edge of the class distributions in feature space (support vectors). This should allow the definition of the most informative training samples prior to the analysis. An approach to identify informative training samples was demonstrated for the classification of agricultural classes in south-western part of Punjab state, India. A small, intelligently selected, training data set was acquired in the field with the aid of ancillary information. This data set contained the data from training sites that were predicted before the classification to be amongst the most informative for a SVM classification. The intelligent training collection scheme yielded a classification of comparable accuracy, ~91%, to one derived using a larger training set acquired by a conventional approach. Moreover, from inspection of the training sets it was apparent that the intelligently defined training set contained a greater proportion of support vectors (0.70), useful training sites, than that acquired by the conventional approach (0.41). By focusing on the most informative training samples, the intelligent scheme required less investment in training than the conventional approach and its adoption would have reduced total financial outlay in classification production and evaluation by ~26%. Additionally, the analysis highlighted the possibility to further reduce the training set size without any significant negative impact on classification accuracy.