KOMBINASI TRANFORMASI SPEKTRAL DALAM KLASIFIKASI BERBASIS OBJEK

Land cover extraction is commonly used with pixel-based classification. However, this classification only uses spectral information and ignores the spatial information. This condition is an interesting point for the research use of spectral information and spatial information for land cover classification. The classification method is object based classification. This study aims to assess the accuracy of object-based classification results using Aster Vnir imagery with combination spectral transformation. The segmentation process uses the multiresolution segmentation and the classification process uses the nearest neighbor algoritm. The results show that the object based classification that uses Aster Vnir combination with Ndvi can improve the accuracy of the classification result, only the increase is not able to produce acceptable accuracy (> 85%). The accuracy value level I to III, respectively for 82.45%, 80.98% and 70.88%. The use of a bands combination just influences the particular land cover objects. The spatial pattern be possessed that relatively the same but the different shapes between object detail land cover. Aster Vnir imagery classification results have details better shape compared with classification result of Aster Vnir with the combination of spectral transformation. Indicated by the difference between density patch and landscape shape index parameter a small value.

1.  UEU-Journal-20235-11_1378.pdf - 952 KB