International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Publications Copernicus
Download
Citation
Volume XLII-4/W16
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLII-4/W16, 503–509, 2019
https://doi.org/10.5194/isprs-archives-XLII-4-W16-503-2019
© Author(s) 2019. This work is distributed under
the Creative Commons Attribution 4.0 License.
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLII-4/W16, 503–509, 2019
https://doi.org/10.5194/isprs-archives-XLII-4-W16-503-2019
© Author(s) 2019. This work is distributed under
the Creative Commons Attribution 4.0 License.

  01 Oct 2019

01 Oct 2019

ACCURACY OF UNSUPERVISED CLASSIFICATION TO DETERMINE CORAL HEALTH USING SPOT-6 AND SENTINEL-2A

N. Nurdin1,3, Supriadi1, M. Lanuru1, M. Akbar AS4, I. Kartika1, and T. Komatsu2,3 N. Nurdin et al.
  • 1Marine Science Department, Hasanuddin University, Makassar, 90245, Indonesia
  • 2Atmosphere and Ocean Research Institute, The University of Tokyo, Kashiwa 277-8564, Japan
  • 3Present affiliation: Yokohama College of Commerce, Yokohama 230-8577, Japan
  • 4Research and Development Center for Marine, Coast, and Small Island, Hasanuddin University, Jl.Perintis Kemerdekaan km.10, Makassar, 90245, Indonesia

Keywords: Pulau Barrang Caddi, Spectral, IsoData, K-Means, Spermonde Archipelago

Abstract. Characteristics of corals spectral from different species are expected to have optically different characters. The aims of this research are to compare unsupervised classification between IsoData and K-Means methods with Lyzenga application, and to analyze the precision of SPOT-6 and Sentinel-2A satellite imagery in classsifying shallow water habitat. The image processing are atmosferic correction, cropping, masking, Depth Invariant Index, Unsupervised classification, ground truthing, reclassify, accuracy assessment, and shallow water habitat spectral reflectance analysis. Rubble and dead coral with algae were indicating as coral death due to either damaging human activity or natural death such as bleaching. The accuracy of unsupervised classification IsoData and K-Means method have the same accuracy 62.50%. The IsoData method is better detected live coral and algae. Rubble were dominant detected in K-Means method.