Oktavian, Syifa Laili Hapsari (2020) Penerapan Metode Faster Regional – Convolutional Neural Network (Faster R – CNN) untuk Klasifikasi Jenis Kerusakan Jalan. Other thesis, Institut Teknologi Sepuluh Nopember.
Preview |
Text
06111540000035_Undergraduate_Thesis.pdf - Accepted Version Download (3MB) | Preview |
Abstract
Jalan merupakan prasarana lalu lintas untuk mendukung mobilitas masyarakat, pertumbuhan ekonomi, dan pembangunan nasional. Kerusakan jalan dapat menyebabkan arus lalu lintas terhambat. Untuk melakukan perbaikan jalan, salah satu faktor yang perlu diketahui adalah jenis kerusakan jalan. Selama ini, klasifikasi kerusakan jalan dilakukan secara manual. Pada tugas akhir ini telah dilakukan klasifikasi kerusakan jalan secara otomatis dengan metode Faster Regional – Convolutional Neural Network (Faster R – CNN). Terdapat tiga tahap utama dalam klasifikasi kerusakan jalan, pertama tahap preprocessing untuk memperbaiki kualitas data citra, kedua tahap training untuk melatih sistem dalam mengenali jenis kerusakan jalan, dan ketiga tahap klasifikasi untuk mengklasifikasikan kerusakan jalan. Pada klasifikasi yang dilakukan kerusakan jalan dibagi menjadi tiga kelas, yaitu retak aligator, retak garis, dan lubang. Hasil klasifikasi menunjukkan bahwa metode Faster R – CNN dapat mengklasifikasikan kerusakan jalan secara baik dengan akurasi sebesar 95.73% pada 1,200 data uji coba yang digunakan.
=================================================================================================================================
Pavement are traffic infrastructure to support community mobility, economic growth and national development. Pavement distress can cause traffic flow obstructions. To carry out pavement repairs, one of the factors that needs to be known is the types of pavement distress. During this time, the classification of pavement distress is done manually. In this final project the classification of pavement distress has been done automatically with Faster Regional-Convolutional Neural Network (Faster R-CNN) method. There are three main steps in the classification of pavement distress, the first step is preprocessing to improve the quality of image data, the second step is to train the system in recognizing the type of pavement distress, and the third step is to classify pavement distress. In this classification the type of pavement distress is divided into three classes, those are alligator cracks, line cracks, and potholes. The classification results show that the Faster R-CNN method can classify pavement distress properly with accuracy of 95.73% on the 1,200 trial data used.
| Item Type: | Thesis (Other) |
|---|---|
| Additional Information: | RSMa 006.42 Okt p-1 |
| Uncontrolled Keywords: | Kerusakan Jalan, Pengolahan Citra Digital, Faster R – CNN |
| Subjects: | Q Science > QA Mathematics > QA336 Artificial Intelligence Q Science > QA Mathematics > QA76.87 Neural networks (Computer Science) T Technology > TA Engineering (General). Civil engineering (General) > TA1637 Image processing--Digital techniques |
| Divisions: | Faculty of Science and Data Analytics (SCIENTICS) > Mathematics > 44201-(S1) Undergraduate Thesis |
| Depositing User: | Oktavian Syifa Laili Hapsari |
| Date Deposited: | 08 May 2023 02:14 |
| Last Modified: | 08 May 2023 02:14 |
| URI: | http://repository.its.ac.id/id/eprint/73049 |
Actions (login required)
 |
View Item |