Wiratama, Afif Rayhan (2026) Analisis Klasifikasi Tutupan Lahan Berbasis Digitasi Manual Dan Metode Otomatis (OBIA) Pada Citra Ortofoto (Studi Kasus: Stadion Swarna Bhumi, Kab. Muaro Jambi). Other thesis, Institut Teknologi Sepuluh Nopember.
![[thumbnail of 5016201061-Undergradute-Thesis.pdf]](http://repository.its.ac.id/style/images/fileicons/text.png) |
Text
5016201061-Undergradute-Thesis.pdf Restricted to Repository staff only Download (7MB) | Request a copy |
Abstract
Tutupan lahan merupakan salah satu informasi penting yang digunakan untuk mengetahui kondisi dan pemanfaatan suatu wilayah. Perkembangan teknologi penginderaan jauh melalui penggunaan Unmanned Aerial Vehicle (UAV) memungkinkan diperolehnya citra ortofoto beresolusi tinggi yang dapat dimanfaatkan dalam pemetaan tutupan lahan. Penelitian ini bertujuan mengklasifikasikan tutupan lahan menggunakan metode digitasi manual dan metode Object-Based Image Analysis (OBIA) serta menganalisis hasil kedua metode tersebut pada kawasan sekitar Stadion Swarna Bhumi, Kabupaten Muaro Jambi. Data yang digunakan berupa ortofoto hasil akuisisi UAV Fixed Wing Trinity F90+ VTOL dengan tinggi terbang 245 meter, side overlap 75%, forward overlap 60%, dan Ground Sampling Distance (GSD) sebesar 3,18 cm/piksel. Tahapan penelitian meliputi pengolahan ortofoto, uji akurasi horizontal dan vertikal, proses digitasi manual, validasi topologi, segmentasi mean shift, pembuatan training sample, klasifikasi OBIA, serta uji akurasi menggunakan matriks konfusi. Hasil uji akurasi horizontal menunjukkan nilai RMSE sebesar 1,5905 meter dan CE90 sebesar 2,4136 meter yang memenuhi spesifikasi ketelitian Peta Skala 1:5.000 Kelas 2 dan Peta Skala 1:10.000 Kelas 1 berdasarkan Peraturan Badan Informasi Geospasial Nomor 6 Tahun 2018, sedangkan uji akurasi vertikal menghasilkan nilai RMSE sebesar 3,0535 meter dan LE90 sebesar 5,0227 meter, sehingga ortofoto beserta model elevasi yang dihasilkan layak digunakan sebagai data dasar penelitian. Klasifikasi tutupan lahan menghasilkan empat kelas, yaitu lahan terbangun, lahan terbuka kosong, badan air, dan vegetasi. Metode digitasi manual menghasilkan luas lahan terbangun sebesar 22,232 ha, lahan terbuka kosong 18,902 ha, badan air 6,671 ha, dan vegetasi 132,467 ha, sedangkan metode OBIA menghasilkan luas lahan terbangun 14,718 ha, lahan terbuka kosong 35,836 ha, badan air 9,444 ha, dan vegetasi 120,273 ha. Hasil validasi topologi menunjukkan tidak terdapat kesalahan gap maupun overlap, sedangkan uji akurasi klasifikasi OBIA menghasilkan overall accuracy sebesar 84,7% dan koefisien kappa sebesar 0,678 yang menunjukkan tingkat ketelitian klasifikasi yang baik. Berdasarkan hasil penelitian, metode digitasi manual menghasilkan batas objek yang lebih detail dan presisi, sedangkan metode OBIA mampu mengklasifikasikan tutupan lahan secara otomatis dengan tingkat akurasi yang baik sehingga menjadi alternatif yang efektif dalam pemetaan tutupan lahan.
=================================================================================================================================
Land cover is one of the important information used to determine the condition and utilization of an area. The development of remote sensing technology through the use of Unmanned Aerial Vehicles (UAVs) allows the acquisition of high-resolution orthophoto images that can be used in land cover mapping. This study aims to classify land cover using manual digitization and Object-Based Image Analysis (OBIA) methods and analyze the results of both methods in the area around Swarna Bhumi Stadium, Muaro Jambi Regency. The data used are orthophotos acquired by the Trinity F90+ VTOL Fixed Wing UAV with a flight height of 245 meters, side overlap of 75%, forward overlap of 60%, and Ground Sampling Distance (GSD) of 3.18 cm/pixel. The research stages include orthophoto processing, horizontal and vertical accuracy tests, manual digitization processes, topology validation, mean shift segmentation, training sample creation, OBIA classification, and accuracy tests using confusion matrices. The results of the horizontal accuracy test showed an RMSE value of 1.5905 meters and a CE90 of 2.4136 meters which met the accuracy specifications of the 1:5,000 Class 2 Scale Map and the 1:10,000 Class 1 Scale Map based on Geospatial Information Agency Regulation Number 6 of 2018, while the vertical accuracy test produced an RMSE value of 3.0535 meters and a LE90 of 5.0227 meters, so that the resulting orthophoto and elevation model are suitable for use as basic research data. Land cover classification produces four classes, namely built-up land, empty open land, water bodies, and vegetation. The manual digitization method produced a built-up area of 22,232 ha, empty open land of 18,902 ha, water bodies of 6,671 ha, and vegetation of 132,467 ha, while the OBIA method produced a built-up area of 14,718 ha, empty open land of 35,836 ha, water bodies of 9,444 ha, and vegetation of 120,273 ha. The topology validation results showed no gap or overlap errors, while the OBIA classification accuracy test produced an overall accuracy of 84.7% and a kappa coefficient of 0.678, indicating a good level of classification accuracy. Based on the research results, the manual digitization method produced more detailed and precise object boundaries, while the OBIA method was able to classify land cover automatically with a good level of accuracy, making it an effective alternative in land cover mapping.
| Item Type: | Thesis (Other) |
|---|---|
| Uncontrolled Keywords: | Digitasi Manual, Object-Based Image Analysis (OBIA), Ortofoto, Tutupan Lahan, Manual Digitization, Object-Based Image Analysis (OBIA), Orthophoto, Land Cover |
| Subjects: | G Geography. Anthropology. Recreation > G Geography (General) > G70.212 ArcGIS. Geographic information systems. G Geography. Anthropology. Recreation > G Geography (General) > G70.217 Geospatial data T Technology > TA Engineering (General). Civil engineering (General) > TA593 Orthophotography T Technology > TR Photography > TR810 Aerial photography U Military Science > UG1242 Drone aircraft--Control systems. (unmanned vehicle) |
| Divisions: | Faculty of Civil, Planning, and Geo Engineering (CIVPLAN) > Geomatics Engineering > 29202-(S1) Undergraduate Thesis |
| Depositing User: | Afif Rayhan Wiratama |
| Date Deposited: | 28 Jul 2026 07:44 |
| Last Modified: | 28 Jul 2026 07:46 |
| URI: | http://repository.its.ac.id/id/eprint/138308 |
Actions (login required)
 |
View Item |