Muslim, Muhammad (2019) Identifikasi Lubang Pada Jalan Menggunakan Pengolahan Citra Digital. Masters thesis, Institut Teknologi Sepuluh Nopember.
|
Text
06111750012011-Master_Thesis.pdf Restricted to Repository staff only Download (11MB) | Request a copy |
Abstract
Pada saat ini pengecekan jalan dilakukan secara manual. Pengecekan jalan secara manual masih memiliki banyak kekurangan antara lain membutuhkan banyak waktu, membutuhkan banyak biaya, berbahaya, dan kurangnya akurasi dari informasi data. Oleh karena itu, dibutuhkan pengecekan jalan secara otomatis. Pada penelitian ini dikembangkan suatu sistem identifkasi kerusakan jalan khususnya lubang, berbasis video digital, dengan menggunakan pengolahan citra digital. Pengolahan citra digital mempunyai keunggulan
dalam mendeteksi objek. Aplikasi dari pengolahan citra digital diantaranya adalah deteksi kecacatan peluru, deteksi kecacatan kerammik, dan lain-lain. Tahapan-tahapan pada penelitian ini antara lain pre-processing untuk memperbaiki kualitas citra, segmentasi untuk membedakan antara objek dan
background, morfologi untuk menyempurnakan bentuk objek, labeling dan tracking untuk memberi ID dan mengetahui objek yang sama pada urutan frame, dan tahapan terakhir adalah perhitungan jumlah lubang pada jalan. Pada proses morfologi menggunakan tiga bentuk dan tiga ukuran elemen struktur. Bentuk elemen struktur yang digunakan adalah rectangle, ellipse, dan cross, sedangkan ukuran elemen struktur adalah 11x11, 13x13, 15x15, dan 17x17. Pada penelitian ini hasil uji coba terbaik ditunjukkan pada bentuk elemen struktur rectangle dan ukuran 13x13 dengan nilai rata-rata akurasi
84%, presisi 90%, dan recall 100%.
=================================================================================================================================
At this time the road checking is done manually. Road checking manually still has many disadvantages, among others, requiring a lot of time, requiring high costs, being dangerous, and lacking accuracy in data information. Therefore, automatic road checking is needed. In this study, a road distress identification system, especially for potholes, was developed based on digital video using digital image processing. Digital image processing has advantages in detecting objects. Applications of digital image processing include the detection of bullet defects, detection of ceramic defects, and others. The stages in this study include pre-processing to improve image quality, segmentation to distinguish between objects and background, morphology to perfect the shape of the object, labeling and tracking to assign IDs and identify the same object across frames, and the final step is calculating the number of potholes on the road. The morphology process uses three shapes and three structural elements. The shapes of the structural elements used are rectangle, ellipse, and cross, while the sizes of the structural elements are 11×11, 13×13, 15×15, and 17×17. In this study, the best trial results were obtained using a rectangle structural element with a size of 13×13, achieving an average accuracy of 84%, precision of 90%, and recall of 100%.
| Item Type: | Thesis (Masters) |
|---|---|
| Uncontrolled Keywords: | Kerusakan jalan, lubang, Morfologi, Video Digital |
| Subjects: | T Technology > TA Engineering (General). Civil engineering (General) > TA1637 Image processing--Digital techniques. Image analysis--Data processing. T Technology > TE Highway engineering. Roads and pavements T Technology > TE Highway engineering. Roads and pavements > TE7 Transportation--Planning |
| Divisions: | Faculty of Mathematics and Science > Mathematics > 44101-(S2) Master Thesis |
| Depositing User: | Muhammad Muslim Muslim |
| Date Deposited: | 23 Jul 2026 01:45 |
| Last Modified: | 23 Jul 2026 01:45 |
| URI: | http://repository.its.ac.id/id/eprint/68231 |
Actions (login required)
![]() |
View Item |
