| Abstrak/Abstract |
The low number of water penetration bands in multispectral images limits the maximum descriptive resolution and the accuracy of the resulting benthic habitat maps, especially at higher levels of benthic habitat scheme complexities. This research aimed at exploiting the spectral performance of multispectral images for benthic habitats mapping using image rotation techniques. Karimunjawa Islands are selected as the study areas. Principle Component Analysis (PCA) and Independent Component Analysis (PCA) were applied on Worldview-2 prior to image classifications. The inputs for PCA and ICA are deglint bands and water column-corrected bands. Field benthic data collected from photo-transect were used to train the rotated datasets in the classification process and to assess the accuracy of the resulting benthic habitat maps. Three levels of benthic habitat classification schemes were constructed based on the variation of benthic habitats insitu, which covers the variations of coral reefs, seagrass, macro algae, and bare substratum. The results show that the application of image rotations on Worldview-2 improves the overall accuracy of benthic habitats mapping and the rotated datasets become more effective as the classification scheme complexities increase. |
