Pengenalan Rambu Lalu Lintas Indonesia Menggunakan Mask R-CNN

Angellina, Nia (2021) Pengenalan Rambu Lalu Lintas Indonesia Menggunakan Mask R-CNN. Undergraduate thesis, Institut Teknologi Sepuluh Nopember.

Text 07211740000014-Undergraduate_Thesis.pdf - Accepted Version Restricted to Repository staff only until 1 October 2023. Download (2MB) | Request a copy

Abstract

Seiring dengan bertambahnya jumlah mobil yang ada dan berkembangnya teknologi saat ini, terlihat jelas masih banyaknya kecelakaan yang terjadi dan pelanggaran rambu lalu lintas. Maka, autonomous car atau mobil otomatis dikembangkan untuk mengurangi tingkat kecelakaan yang terjadi. Sebagian be sar pengemudi melewatkan rambu lalu lintas karena rintangan yang berbeda dan kurangnya perhatian. Sehingga, autonomous car atau mobil otomatis
diharapkan bisa berjalan sendiri dan memiliki kemampuan
mendeteksi lingkungan di sekitarnya. Pada tugas akhir ini adalah mengerjakan program sistem pengenalan rambu lalu lintas menggunakan Mask R-CNN. Tahapannya yaitu training dataset rambu lalu lintas lalu nanti akan menghasilkan model rambu lalu lintas. Lalu dilakukan testing antara dataset testing dengan model yang sudah diperoleh dari training. Lalu didapatkan hasilnya berupa pengenalan rambu lalu lintas. Diharapakan mampu mengenali rambu lalu lintas Indonesia dengan cepat dan tepat
=====================================================================================================
Along with the increasing number of existing cars and the development of current technology, it is clear that there are still many accidents that occur and violations of traffic signs. So, autonomous cars or automatic cars are developed to reduce the rate of accidents that happen. Most of the drivers miss the traffic signs due to different obstacles and lack of attention. Thus, autonomous cars are expected to be able to run on their own and have the ability to detect the surrounding environment. In this final project is working on a traffic sign recognition system program using Mask R-CNN. The stage is the training of the traffic sign dataset which will later produce a traffic sign model. Then testing is carried out between the testing dataset and the model that has been obtained from training.
Then the results obtained in the form of the introduction of traffic signs. It is hoped that they will be able to recognize Indonesian traffic signs quickly and accurately

Item Type:	Thesis (Undergraduate)
Uncontrolled Keywords:	Autonomous Car, Rambu Lalu Lintas, Deep Learning, Image Processing, Mask R-CNN, Traffic Sign
Subjects:	R Medicine > R Medicine (General) > R858 Deep Learning T Technology > T Technology (General)
Divisions:	Faculty of Intelligent Electrical and Informatics Technology (ELECTICS) > Computer Engineering > 90243-(S1) Undergraduate Thesis
Depositing User:	Nia Angellina
Date Deposited:	07 Sep 2021 09:04
Last Modified:	07 Sep 2021 09:04
URI:	http://repository.its.ac.id/id/eprint/91764

Actions (login required)

View Item