OBJECT BASED MAPPING ON BENTHIC HABITAT USING SENTINEL-2 IMAGERY OF THE WANGI-WANGI ISLAND WATERS OF THE WAKATOBI DISTRICT

被引:8
作者
Mastu, La Ode Khairum [1 ]
Nababan, Bisman [2 ]
Panjaitan, James P. [2 ]
机构
[1] IPB, Sekolah Pascasarjana, Program Studi Teknol Kelautan, Bogor, Indonesia
[2] FPIK IPB, Dept Ilmu & Teknol Kelautan, Bogor, Indonesia
来源
JURNAL ILMU DAN TEKNOLOGI KELAUTAN TROPIS | 2018年 / 10卷 / 02期
关键词
mapping; benthic habitats; OBIA; Sentinel-2; Wangi-wangi Island waters;
D O I
10.29244/jitkt.v10i2.21039
中图分类号
Q17 [水生生物学];
学科分类号
071004 ;
摘要
Research on benthic habitat mapping in the Wangi-wangi Island waters was very limited. Therefore the spatial data availability of benthic habitat in this area is also very limited. The purposes of this study were to map the shallow water benthic habitats using Sentinel-2 image based on object-based classification method (OBIA) and to calculate the accuracy level of benthic habitat classification results in the Wangi-wangi Island waters of the Wakatobi District. This research was conducted in the Wangi-wangi Island waters around Sombu Dive waters and it's surroundings. The study used satellite Sentinel-2 data with 10x10 m(2) spatial resolution acquired on 4 April 2017 and the field data were acquired in March - April 2017. Satellite image was classified with OBIA method using contextual editing at level 1. At level 2, we used supervised classification with some algorithms such as support vector machine (SVM), decision tree (DT), Bayesian, and k-nearest neighbour (KNN) with input themathic layer from field data. The classification of benthic habitats was performed in 12 and 9 classes with the application of segmentation-optimization scale of 1, 1.5, 2, and 2.5. Based on OBIA method, benthic habitat can be mapped with the best overall accuracy of 60.4% and 64.1% for the image classification of 12 and 9 classes, respectively with SVM algorithm and the optimum segmentation scale of 2.
引用
收藏
页码:381 / 396
页数:16
相关论文
共 39 条
[1]  
Adji A.S., 2014, MAR RES INDONES, V39, P73, DOI [10.14203/mri.v39i2.87, DOI 10.14203/MRI.V39I2.87]
[2]   Multi-site evaluation of IKONOS data for classification of tropical coral reef environments [J].
Andréfouët, S ;
Kramer, P ;
Torres-Pulliza, D ;
Joyce, KE ;
Hochberg, EJ ;
Garza-Pérez, R ;
Mumby, PJ ;
Riegl, B ;
Yamano, H ;
White, WH ;
Zubia, M ;
Brock, JC ;
Phinn, SR ;
Naseer, A ;
Hatcher, BG ;
Muller-Karger, FE .
REMOTE SENSING OF ENVIRONMENT, 2003, 88 (1-2) :128-143
[3]  
Anggoro A, 2017, J PENGINDERAAN JAUH, V14, P89
[4]  
Anggoro A., 2015, JURNAL PENGINDERAAN, V1, P1
[5]  
Anggoro A., 2015, THESIS
[6]  
[Anonymous], MATER CHARACT, DOI DOI 10.1016/J.MATCHAR.2009.07.002
[7]  
Balai Taman Nasional Wakatobi [BTNW], 2009, INF TAM NAS WAK
[8]   Mapping the distribution of coral reefs and associated sublittoral habitats in Pacific Panama: a comparison of optical satellite sensors and classification methodologies [J].
Benfield, S. L. ;
Guzman, H. M. ;
Mair, J. M. ;
Young, J. A. T. .
INTERNATIONAL JOURNAL OF REMOTE SENSING, 2007, 28 (22) :5047-5070
[9]   Object based image analysis for remote sensing [J].
Blaschke, T. .
ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING, 2010, 65 (01) :2-16
[10]  
Bradski G., 2008, LEARNING OPENCV COMP, DOI 10.1109/MRA.2009.933612