Kalibrasi Kamera Omnivision pada Mobile Robot Menggunakan Machine Learning

Maulana, Azzam Wildan and Muhtadin, Muhtadin and Zaini, Ahmad (2024) Kalibrasi Kamera Omnivision pada Mobile Robot Menggunakan Machine Learning. Other thesis, Institut Teknologi Sepuluh Nopember.

Text Tugas Akhir wildan fix (1).pdf - Accepted Version Restricted to Repository staff only until 1 October 2026. Download (4MB) | Request a copy

Abstract

Mobile Robot adalah sebuah robot yang bisa bergerak dengan mudah. Gerakan dari robot
tersebut bisa menyebabkan terjadinya pergeseran sudut kamera. Pergeseran ini bisa disebabkan
karena manufaktur pemasangan kamera yang salah atau terjadi tabrakan pada robot. Pergeseran
sudut kamera akan menyebabkan interpretasi data kamera terhadap dunia luar menjadi salah.
Penggunaan metode Machine Learning pada kalibrasi kamera Omnivision dapat memperbaiki
interpretasi kamera yang salah tanpa dipengaruhi oleh proses pembuatan dan pemasangan kam-
era Omnivision. Machine Learning yang digunakan adalah Multi Layer Perceptron Neural Net-
work dengan activation function berupa sigmoid. Hasil dari Machine Learning akan diubah
menjadi sebuah Lookup Table yang nantinya akan digunakan pada proses komputasi vision
pada robot. Metode tersebut lebih baik daripada metode lama regresi polinomial. Hal itu dapat
dilihat dari sisi akurasi dan presisi yang dihasilkan oleh metode Machine Learning lebih baik
daripada metode regresi polinomial. Error akurasi metode Machine Learning sebesar 10.84 cm
sedangkan metode regresi polinomial sebesar 20.77 cm. Error presisi metode Machine Learn-
ing sebesar 1.20 cm dan 4.10 cm sedangkan metode regresi polinomial sebesar 10.01 cm dan
11.32 cm. Dengan menggunakan metode Machine Learning pada kalibrasi kamera Omnivision,
maka robot dapat bergerak dengan lebih baik.
================================================================================================================
Mobile Robot is a robot that can easily move. The movement of the robot can cause the
camera angle to shift. This shift can be caused by the wrong manufacturing of the camera in-
stallation or collision on the robot. The camera angle shift will cause the real world camera’s
interpretation wrong. The use of Machine Learning methods in Omnivision camera calibra-
tion can correct the wrong camera interpretation without being influenced by the Omnivision
camera manufacturing and installation process. The Machine Learning used is a Multi Layer
Perceptron Neural Network with sigmoid as activation function. The results of Machine Learn-
ing will be converted into Lookup Table which will be used in the vision computation process of
the robot. This method is better than the old polynomial regression method. This can be seen
from the accuracy and precision produced by the Machine Learning method which is better
than the polynomial regression method. The accuracy error of the Machine Learning method is
10.84 cm while the polynomial regression method is 20.77 cm. The precision error of the Ma-
chine Learning method is 1.20 cm and 4.10 cm while the polynomial regression method is 10.01
cm and 11.32 cm. By using the Machine Learning method in Omnivision camera calibration,
the robot can move better.

Item Type:	Thesis (Other)
Uncontrolled Keywords:	Omnivision, Calibration, IRIS, Omnivision, Kalibrasi, IRIS
Subjects:	T Technology > TJ Mechanical engineering and machinery > TJ211 Robotics. T Technology > TJ Mechanical engineering and machinery > TJ211.415 Mobile robots
Divisions:	Faculty of Intelligent Electrical and Informatics Technology (ELECTICS) > Computer Engineering > 90243-(S1) Undergraduate Thesis
Depositing User:	Azzam Wildan Maulana
Date Deposited:	02 Aug 2024 07:47
Last Modified:	02 Aug 2024 07:47
URI:	http://repository.its.ac.id/id/eprint/111317

Actions (login required)

View Item