IPB University Logo

SCIENTIFIC REPOSITORY

IPB University Scientific Repository collects, disseminates, and provides persistent and reliable access to the research and scholarship of faculty, staff, and students at IPB University

AI Repository
 
Building and Categories


      View Item 
      •   IPB Repository
      • Final Assignments
      • Undergraduate Final Assignments
      • UT - Faculty of Agriculture
      • UF - Soil Science and Land Resources
      • View Item
      •   IPB Repository
      • Final Assignments
      • Undergraduate Final Assignments
      • UT - Faculty of Agriculture
      • UF - Soil Science and Land Resources
      • View Item
      JavaScript is disabled for your browser. Some features of this site may not work without it.

      EVALUASI KINERJA CITRA RGB DAN MULTISPEKTRAL UAV UNTUK PEMETAAN TUTUPAN SAWAH DI KAWASAN TRANSMIGRASI MAHALONA, LUWU TIMUR

      Thumbnail
      View/Open
      Cover (832.3Kb)
      Fulltext (2.195Mb)
      Lampiran (408.8Kb)
      Date
      2026
      Jenis/Type
      Skripsi
      Subtype
      Undergraduate Theses
      Author
      FERRANDO, INDIGO
      Iskandar, Wahyu
      Munibah, Khursatul
      Metadata
      Show full item record
      Abstract
      Pemantauan lahan sawah di kawasan transmigrasi masih banyak mengandalkan observasi lapangan yang membutuhkan waktu dan tenaga besar, sehingga diperlukan pendekatan berbasis citra drone yang lebih cepat dan akurat. Penelitian ini bertujuan mengevaluasi kemampuan kamera Unmanned Aerial Vehicle (UAV) RGB dan multispektral untuk pemantauan sawah, serta membandingkan akurasi klasifikasi tutupan lahan menggunakan algoritma Random Forest berbasis kedua jenis citra tersebut pada fase tanam dan fase panen di Kawasan Transmigrasi Mahalona, Kabupaten Luwu Timur. Citra diakuisisi menggunakan UAV pada ketinggian 50 meter, diolah secara fotogrametri, dan diklasifikasikan ke dalam enam kelas tutupan lahan (area terbangun, badan air, lahan terbuka, pematang, vegetasi padi, vegetasi pohon ),menggunakan 600 titik sampel. Hasil menunjukkan kamera RGB memiliki resolusi spasial (GSD 1,15 cm/piksel) dan ketelitian geolokasi vertikal (RMSE Z 0,0086 m) yang lebih baik dibandingkan kamera multispektral (GSD 1,87 cm/piksel; RMSE Z 0,032 m), sedangkan kualitas kalibrasi kedua kamera hampir setara. Pada klasifikasi tutupan lahan, citra multispektral cenderung menghasilkan akurasi keseluruhan lebih tinggi dibandingkan RGB pada kedua fase, yaitu 71% berbanding 67% pada fase tanam dan 72% berbanding 70% pada fase panen, dengan selisih terbesar pada fase tanam terutama pada kelas pematang. Kelas pematang paling sulit diklasifikasikan pada sebagian besar skenario akibat piksel campuran. Temuan ini menunjukkan kamera RGB lebih sesuai untuk pemetaan geometrik, sedangkan kamera multispektral lebih unggul untuk klasifikasi tutupan lahan, sehingga pemilihan sensor UAV perlu disesuaikan dengan tujuan pemantauan sawah di kawasan transmigrasi.
       
      Paddy field monitoring in transmigration areas still largely relies on timeconsuming field observation, requiring a faster, more accurate aerial imagery-based approach. This study evaluated the capability of RGB and multispectral Unmanned Aerial Vehicle (UAV) cameras for paddy field monitoring and compared the accuracy of land cover classification using the Random Forest algorithm based on both imagery types during the planting and vegetative growth phases in the Mahalona Transmigration Area, East Luwu Regency. Imagery was acquired using a Real Time Kinematic-equipped UAV at 50 meters altitude, processed photogrammetrically, and classified into six land cover classes (Built-up area, Water bodies, Open land, Bunds, Rice vegetation, Tree vegetation) using 600 sample points. Results showed the RGB camera had better spatial resolution and vertical geolocation accuracy, while calibration quality of both cameras was nearly equal. For classification, multispectral imagery consistently achieved higher overall accuracy than RGB in both phases, with the largest gap in the planting phase, particularly for the levee class, whereas bare land and rice vegetation remained difficult to distinguish using either sensor. These findings indicate the RGB camera is more suitable for geometric spacial, whereas the multispectral camera performs better for land cover classification, so UAV sensor selection should match specific monitoring needs in transmigration areas.
       
      URI
      http://repository.ipb.ac.id/handle/123456789/180181
      Collections
      • UF - Soil Science and Land Resources [2896]

      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