dc.contributor.advisor | Jaya, I Nengah Surati | |
dc.contributor.author | Putri, Ardhya Zahra Gunara | |
dc.date.accessioned | 2022-01-01T09:43:46Z | |
dc.date.available | 2022-01-01T09:43:46Z | |
dc.date.issued | 2021-12-31 | |
dc.identifier.uri | http://repository.ipb.ac.id/handle/123456789/110413 | |
dc.description.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%. | id |
dc.description.abstract | 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%. | id |
dc.language.iso | id | id |
dc.publisher | IPB University | id |
dc.title | Kajian Metode Segmentasi Watershed pada Klasifikasi Tutupan Tajuk Hutan Mangrove: Studi Kasus di Kalimantan Barat | id |
dc.title.alternative | Study of Watershed Segmentation Method on Classification of Mangrove Crown Closure: a Case Study in West Kalimantan | id |
dc.type | Undergraduate Thesis | id |
dc.subject.keyword | algoritma watershed | id |
dc.subject.keyword | hutan mangrove | id |
dc.subject.keyword | penutupan tajuk | id |
dc.subject.keyword | segmentasi | id |