Realtime Geotagging pada Unmanned Aerial Vehicle Menggunakan YOLO dan Deep Sort

Putra Suharsono, Ardiar (2026) Realtime Geotagging pada Unmanned Aerial Vehicle Menggunakan YOLO dan Deep Sort. Masters thesis, Institut Teknologi Sepuluh Nopember.

Text 6022241083_Master_Thesis.pdf - Accepted Version Restricted to Repository staff only Download (9MB) | Request a copy

Abstract

Seiring meningkatnya kebutuhan global akan minyak kelapa sawit, efisiensi dalam proses produksi menjadi fokus utama industri perkebunan, termasuk dalam pengelolaan dan manajemen aset perkebunan yang hingga kini masih menghadapi berbagai kendala operasional, seperti luasnya area perkebunan serta karakteristik pohon kelapa sawit dengan ketinggian yang bervariasi, sehingga menyulitkan proses inventarisasi dan pemantauan aset secara manual. Untuk mengatasi keterbatasan metode konvensional dan meningkatkan efektivitas pengelolaan aset, teknologi Unmanned Aerial Vehicle (UAV) menawarkan solusi alternatif yang menjanjikan dengan mengandalkan kemampuannya untuk bergerak secara otomatis didalam perkebunan. Namun diperlukan data posisi dan identitas masing-masing pohon agar pengelolaan dapat diterapkan secara otomatis. Penelitian ini merancang dan mengimplementasikan sistem realtime geotagging berbasis UAV menggunakan algoritma Deep SORT untuk mengidentifikasi, melacak, dan menentukan posisi pohon kelapa sawit secara otomatis dalam area perkebunan. Sistem ini dilengkapi dengan mekanisme pelacakan visual cerdas berbasis neural network dengan model YOLO yang bekerja secara realtime. Data posisi dan identitas pohon kelapa sawit yang diperoleh selanjutnya disimpan dalam basis data sebagai fondasi bagi pengembangan sistem manajemen aset perkebunan yang terintegrasi, efisien, dan berbasis spasial. Dengan menyediakan informasi spasial serta identifikasi individual setiap pohon, sistem ini diharapkan dapat menjadi komponen penting dalam digitalisasi dan otomatisasi pengelolaan aset perkebunan, sekaligus mendukung pengambilan keputusan yang lebih akurat serta peningkatan produktivitas di sektor perkebunan kelapa sawit.
===================================================================================================================================
As global demand for palm oil continues to increase, efficiency in production processes has become a major focus of the plantation industry, particularly in plantation asset management, which still faces various operational challenges. These challenges include the vast size of plantation areas and the varying heights and characteristics of oil palm trees, which complicate manual asset inventory and monitoring processes. To overcome the limitations of conventional methods and improve asset management effectiveness, Unmanned Aerial Vehicle (UAV) technology offers a promising alternative by leveraging its capability to autonomously navigate plantation environments. However, effective automation requires accurate positional and identity data for each individual tree. This research designs and implements a UAV-based real-time geotagging system using the Deep SORT algorithm to automatically identify, track, and determine the positions of oil palm trees within plantation areas. The system is equipped with an intelligent visual tracking mechanism based on a neural network, utilizing the YOLO model to operate in real time. The acquired positional and identity data of oil palm trees are subsequently stored in a database as a foundation for the development of an integrated, efficient, and spatially driven plantation asset management system. By providing spatial information and individual tree identification, the proposed system is expected to become a key component in the digitalization and automation of plantation asset management, supporting more accurate decision-making and enhancing productivity in the oil palm plantation sector.

Item Type:	Thesis (Masters)
Uncontrolled Keywords:	Geotagging, UAV, DeepSORT, YOLO Geotagging, UAV, DeepSORT, YOLO
Subjects:	G Geography. Anthropology. Recreation > G Geography (General) > G70.217 Geospatial data T Technology > TK Electrical engineering. Electronics Nuclear engineering > TK6592.A9 Automatic tracking. T Technology > TL Motor vehicles. Aeronautics. Astronautics > TL152.8 Vehicles, Remotely piloted. Autonomous vehicles. T Technology > TR Photography > TR810 Aerial photography
Divisions:	Faculty of Intelligent Electrical and Informatics Technology (ELECTICS) > Electrical Engineering > 20101-(S2) Master Thesis
Depositing User:	Ardiar Diandra Putra Suharsono
Date Deposited:	21 Jan 2026 08:57
Last Modified:	21 Jan 2026 08:57
URI:	http://repository.its.ac.id/id/eprint/130009

Actions (login required)

View Item