View Item 
      •   IPB Repository
      • Dissertations and Theses
      • Undergraduate Theses
      • UT - Faculty of Forestry and Environment
      • UT - Forest Management
      • View Item
      •   IPB Repository
      • Dissertations and Theses
      • Undergraduate Theses
      • UT - Faculty of Forestry and Environment
      • UT - Forest Management
      • View Item
      JavaScript is disabled for your browser. Some features of this site may not work without it.

      Kajian Metode Segmentasi Watershed pada Klasifikasi Tutupan Tajuk Hutan Mangrove: Studi Kasus di Kalimantan Barat

      Thumbnail
      View/Open
      Cover (464.1Kb)
      Fulltext (1.279Mb)
      Lampiran (226.3Kb)
      Date
      2021-12-31
      Author
      Putri, Ardhya Zahra Gunara
      Jaya, I Nengah Surati
      Metadata
      Show full item record
      Abstract
      Penelitian ini menguji teknik klasifikasi berbasis objek (OBIA) algoritma watershed dalam mendeteksi penutupan tajuk dan gap pada hutan mangrove. Pendekatan OBIA dinilai lebih unggul dari klasifikasi berbasis piksel karena tidak hanya mempertimbangkan aspek spektral tetapi juga spasial. Algoritma watershed adalah salah satu algortima yang digunakan secara luas dalam klasifikasi digital. Untuk mengetahui keterhandalan klasifikasi OBIA, penelitian ini menggunakan pengujian Overall Accuracy (OA) dan Kappa Accuracy (KA). Penelitian ini menemukan bahwa segmentasi dengan citra asli lebih baik daripada menggunakan citra yang difilter dengan low pass filter. Hasil segmentasi citra tanpa filter rata-rata menghasilkan dihasilkan oleh kombinasi K-10 dengan nilai Overall Accuracy sebesar 96,68% dan nilai Kappa Accuracy sebesar 65,98%. Sementara itu, pengujian segmentasi pada citra dengan filter rata-rata dihasilkan oleh K-06 dengan nilai Overall Accuracy sebesar 94,22% dan nilai Kappa Accuracy sebesar 50,01%.
       
      This study examined the watershed algorithm of object-based classification (OBIA) to detect canopy cover and gaps in mangrove forests. The OBIA approach is considered superior to the pixel-based classification because it not only considers spectral but also spatial aspects. The examined watershed algorithm is a method for image segmentation that is widely used for digital classification. To evaluate the segmentation performance, the study applied the Overall Accuracy (OA) and Kappa Accuracy (KA). The study found that the use of the original image is better than using the filtered image with a low pass filter. The use of image segmentation without an mean filter was provided by the K-10 with an Overall Accuracy value of 96.68% and a Kappa Accuracy value of 65.98%. Meanwhile, the image segmentation test with the filtered-images was obtained from the K-06 combination with an Overall Accuracy value of 94.22% and a Kappa Accuracy value of 50.01%.
       
      URI
      http://repository.ipb.ac.id/handle/123456789/110413
      Collections
      • UT - Forest Management [3204]

      Copyright © 2020 Library of IPB University
      All rights reserved
      Contact Us | Send Feedback
      Indonesia DSpace Group 
      IPB University Scientific Repository
      UIN Syarif Hidayatullah Institutional Repository
      Universitas Jember Digital Repository
        

       

      Browse

      All of IPB RepositoryCollectionsBy Issue DateAuthorsTitlesSubjectsThis CollectionBy Issue DateAuthorsTitlesSubjects

      My Account

      Login

      Application

      google store

      Copyright © 2020 Library of IPB University
      All rights reserved
      Contact Us | Send Feedback
      Indonesia DSpace Group 
      IPB University Scientific Repository
      UIN Syarif Hidayatullah Institutional Repository
      Universitas Jember Digital Repository