Urban Greening Tree Species Classification Based on HSV Colour Space of WorldView-2

Abstract

Feature mining and effective combination of remote sensing data can effectively improve the accuracy of tree species classification; however, the application of some common features in tree species classification needs to be further analysed. In this study, we transformed WorldView-2 RGB bands to hue, saturation and value (HSV) colour space, constructed 56 HSV features, used maximum likelihood classification (MLC) and support vector machine (SVM) to classify tree species based on these data sets and feature combinations to explore which combinations can effectively improve the recognition accuracy. The results show that among the 56 HSV features, the highest classification accuracy (64.2893%) was generated by the HSV feature transformed by the 368 band combination (CBC368). A single HSV feature set could not improve the classification accuracy compared with the spectral band used which produced the HSV. Among the feature sets of all H, all S and all V, the highest classification accuracy (71.7063%) was generated by feature sets all S; it is close but not higher than the classification results obtained using eight bands. Among the combination of two feature sets, the highest classification accuracy (77.5384%) was generated by all S + all V, and the classification accuracy is much higher than that obtained using the eight bands of WorldView-2 (74.0713%, MLC based). When all H, S and V were combined, the classification accuracy reached 77.6251%. Comparative experiments showed that combining all HSV colour spaces transformed by the eight spectral bands of WorldView-2 can effectively improve tree species recognition accuracy.