Inspeksi Jalur Rel Kereta Api Menggunakan Kamera RGB Drone

Sya`bana, Gamma Akbar (2021) Inspeksi Jalur Rel Kereta Api Menggunakan Kamera RGB Drone. Undergraduate thesis, Institut Teknologi Sepuluh Nopember.

[thumbnail of 02311740000077-Undergraduate_Thesis.pdf] Text
02311740000077-Undergraduate_Thesis.pdf - Accepted Version

Download (14MB)
[thumbnail of 02311740000077-Undergraduate_Thesis.pdf] Text
02311740000077-Undergraduate_Thesis.pdf
Restricted to Repository staff only

Download (14MB) | Request a copy
[thumbnail of 02311740000077-Undergraduate_Thesis.pdf] Text
02311740000077-Undergraduate_Thesis.pdf
Restricted to Repository staff only

Download (14MB) | Request a copy

Abstract

Kereta api masih menjadi transportasi favorit di Indonesia, perawatan dan pengecekan pada
jalur rel faktor penting untuk tetap menjaga lancarnya perjalanan kereta api. Salah satu aspek
penting adalah pengecekan pengukuran lebar jalur rel kereta api. Secara konvensional
biasanya langsung dilakukan oleh manusia. Akhir-akhir ini sistem inspeksi berbasis
computer vision sering digunakan karena lebih fleksibel dan mudah dalam penggunaannya.
Penelitian mengenai sistem inspeksi rel kereta api juga suda mulai digunakan, namun masih
menggunakan kamera yang dipasang pada lokomotif kereta. Penggunaan drone untuk
inspeksi jalur rel kereta memberikan data yang cukup akurat untuk mendeteksi dan
memonitoring lebar jalur rel kereta api. Pada penelitian ini menguji akurasi pengukuran rel
kereta api menggunakan drone dengan variasi ketinggian 7 meter dan 15 meter
menggunakan teknik image processing serta pada ketinggian 50 meter untuk basemap uji
data. Hasil menunjukkan akurasi inspeksi rel kereta api pada ketinggian drone 7 meter
mencapai 98,78% dan pada ketinggian 15 meter mencapai 97,41%.
=======================================================================================================
Trains are still the favorite transportation in Indonesia, maintenance and checks on rail lines
are important factors to keep the train journey running smoothly. One important aspect is
checking the measurement of the width of the railroad track. Conventionally it is usually
directly done by humans. Lately, computer vision-based inspection systems are often used
because they are more flexible and easy to use. Research on the railroad inspection system
has also begun to be used, but still uses cameras installed on train locomotives. The use of
drones for railroad inspections provides data that is accurate enough to detect and monitor
the width of the railroad tracks. In this study, we tested the accuracy of measuring railroad
tracks using drones with variations in height of 7 meters and 15 meters using image
processing techniques and at a height of 50 meters for the basemap of the data test. The
results show that the accuracy of railroad inspection at a drone height of 7 meters reaches
98.78% and at an altitude of 15 meters it reaches 97.41%.

Item Type: Thesis (Undergraduate)
Uncontrolled Keywords: Inspection, computer vision, drone, accuracy, image processing, Inspeksi, computer vision, drone, akurasi, image processing
Subjects: T Technology > T Technology (General) > T57.5 Data Processing
Divisions: Faculty of Industrial Technology and Systems Engineering (INDSYS) > Physics Engineering > 30201-(S1) Undergraduate Thesis
Depositing User: Gamma Akbar Sya'bana
Date Deposited: 01 Sep 2021 03:14
Last Modified: 01 Sep 2021 03:14
URI: http://repository.its.ac.id/id/eprint/90950

Actions (login required)

View Item View Item