Firdaus, Muhammad Nadhif (2021) Deteksi Marka Jalan Menggunakan Mask R-CNN. Undergraduate thesis, Institut Teknologi Sepuluh Nopember.
Text
07211540000027-Undergraduate_Thesis.pdf - Accepted Version Restricted to Repository staff only until 1 October 2023. Download (26MB) | Request a copy |
Abstract
Pada penelitian ini digunakan sebuah algoritma untuk mende-
teksi marka jalan berupa garis putus - putus dan garis utuh. Pa-
da implementasinya menggunakan sebuah kamera yang diletakkan
pada mobil untuk mengambil contoh data citra yang kemudian ak-
an diproses sebuah algoritma. Pada proses ini digunakan algoritma
Mask R-CNN yang merupakan salah satu metode dari deteksi objek
yang bagian dari deep learning. Dalam prosesnya algoritma Mask-
RCNN digunakan untuk menunjukkan letak dari objek yang berada
pada gambar dengan membentuk sebuah mask di setiap objeknya.
Dengan begitu hasil yang diharapkan dapat mendeteksi marka jal-
an dengan hasil video yang diambil dari kamera yang diolah oleh
algoritma Mask R-CNN dengan akurasi diatas 90%.
================================================================================================
In this research, an algorithm is used to detect road markings
in the form of dotted lines and solid lines. In its implementation,
it uses a camera that is placed on the car to take samples of image
data which will then be processed by an algorithm. In this process,
the Mask R-CNN algorithm is used, which is one method of object
detection that is part of deep learning. In the process, the Mask-
RCNN algorithm is used to show the location of the objects in the
image by forming a mask on each object. That way the expected
results can detect road markings with video results taken from the
camera processed by the Mask R-CNN algorithm with an accuracy
above 90%.
Item Type: | Thesis (Undergraduate) |
---|---|
Uncontrolled Keywords: | Deteksi Marka Jalan, Mask R-CNN, Deep Lear-ning, Image Processing. Lane Detection, Deep Learning |
Subjects: | T Technology > TA Engineering (General). Civil engineering (General) > TA1637 Image processing--Digital techniques |
Divisions: | Faculty of Information Technology > Computer Engineering > 90243-(S1) Undergraduate Thesis |
Depositing User: | Muhammad Nadhif Firdaus |
Date Deposited: | 02 Sep 2021 15:52 |
Last Modified: | 02 Sep 2021 15:52 |
URI: | http://repository.its.ac.id/id/eprint/91615 |
Actions (login required)
View Item |