Object-Based Classification of Worldview Data for Rehabilitated Vegetation from Mining Site

Vegetation mapping and classification would present valuable information for understanding and evaluating the rehabilitation process in man-made environment of mining site. In this study, object-based classification approach would be applied in rehabilitated vegetation classification using VHR Worldview-2 imagery. The results showed that the largest rehabilitated area occurred in the Hippophae rhamnoides, which can be corresponded the rehabilitated plan. The large trees that include spectrally different features such as trunks, branches and leaves have been successfully segmented into a single image object and finally classified correctly as Pupulus and Locust with the accuracy over than 90%. This study demonstrated how the combination of two new remote sensing technologies in the form of high resolution imagery and OBIA methods can be successfully combined to classify rehabilitated.