Akses terbuka Jurnal SINTA 1
Effect of dataset distribution on automatic road extraction in very high-resolution orthophoto using DeepLab V3+
IAES International Journal of Artificial Intelligence · Vol. 13 No. 2 (2024) · hlm. 1650–1657
- ISSN
- 2252-8938, 2089-4872
- Terbit
- 2024-06-01
- Penerbit
- Institute of Advanced Engineering and Science
- Bahasa
- eng
Abstrak
Road extraction is one of the stages in the map-making process, which has been done manually, takes a long time, and costs a lot. Deep Learning is used to speed up the road extraction process by performing binary semantic segmentation on the image. We propose DeepLab V3+ to produce road extraction from very high-resolution orthophoto for Indonesia study area, which poses many challenges, such as road obstruction by trees, clouds, building shadows, dense traffic, and similarities to rivers and rice fields. We compared the distribution of datasets to obtain the optimal performance of the DeepLab V3+ model in relation to the dataset. The results showed that dataset ratio of 75:10:15 resulted in mean Intersection Over Union (mIoU) of 0.92 and Dice Loss of 0.042. Visually, the results of road extraction are more accurate when compared to the results obtained from different distributions of the dataset.
Kata kunci
Jaringan kolaborasi para penulis
40 penulis · 155 tautan kepenulisan bersama · 53 lintas organisasi · menampilkan 40 yang paling banyak terhubung
Arahkan kursor atau ketuk sebuah nama untuk menyorot rekan penulisnya. Klik dua kali untuk membuka halaman penulis.
- Bandung Institute of Technology
- Telkom University
- National Research and Innovation Agency
- Udayana University
- Institut Teknologi Sepuluh Nopember
- Indonesian National Institute of Aeronautics and Space
- Hasanuddin University
- Organisasi lain
- Afiliasi tidak diketahui
- Organisasi berbeda
- Organisasi sama
- Afiliasi tidak diketahui
- Garis lebih tebal = lebih banyak artikel bersama · lingkaran lebih besar = lebih banyak artikel
Tampilkan sebagai tabel
| Rekan penulis | Organisasi | Artikel bersama |
|---|---|---|
| Ketut Wikantika | Bandung Institute of Technology | 11 |
| Tri Muji Susantoro | National Research and Innovation Agency | 5 |
| Shafarina Wahyu Trisyanti | Bandung Institute of Technology | 4 |
| I Wayan Nuarsa | Udayana University | 3 |
| Riantini Virtriana | Bandung Institute of Technology | 3 |
| Rian Nurtyawan | Bandung Institute of Technology | 2 |
| Asep Saepuloh | Bandung Institute of Technology | 2 |
| Sayidah Sulma | Indonesian National Institute of Aeronautics and Space | 2 |
| Suliantara Suliantara | National Research and Innovation Agency | 2 |
| Herru Lastiadi Setiawan | National Research and Innovation Agency | 2 |
| Adis Jayati | National Research and Innovation Agency | 2 |
| Kurdianto Kurdianto | National Research and Innovation Agency | 2 |
| Sri Astuti | Hasanuddin University | 1 |
| Nurwulan Fitriyanti | Telkom University | 1 |
| Nyoman Bogi Aditya Karna | Telkom University | 1 |
| Nizar Rizky Awany | Telkom University | 1 |
| Muhammad Fajar Firdiansyah | Telkom University | 1 |
| Rafli Noveri Alfariji | Telkom University | 1 |
| Dhea Dearly Herman | Telkom University | 1 |
| Muhammad Risqi Risfianda | Telkom University | 1 |
| Muh Nurkhaliz | Telkom University | 1 |
| Airlangga Baihaqi Wicaksono | Telkom University | 1 |
| Rendy Munadi | Telkom University | 1 |
| Muhammad Ihsan | Bandung Institute of Technology | 1 |
| Muchamad Masykur | Afiliasi tidak diketahui | 1 |
| Andri Hernandi | Bandung Institute of Technology | 1 |
| I Putu Satwika | Institut Teknologi Sepuluh Nopember | 1 |
| Loedi Ratriant | Institut Teknologi Sepuluh Nopember | 1 |
| Yoga Suwarna | Afiliasi tidak diketahui | 1 |
| Elyta Widyaningrum | Afiliasi tidak diketahui | 1 |
| Irland Fardani | Bandung Islamic University | 1 |
| Soni Darmawan | Bandung Institute of Technology | 1 |
| Dudung Muhally Hakim | Bandung Institute of Technology | 1 |
| I Nyoman Dibia | Udayana University | 1 |
Afiliasi berasal dari OpenAlex; metadata OAI-PMH jurnal tidak memuatnya. Penulis tanpa ID OpenAlex dicocokkan berdasarkan nama, sehingga dua orang bisa tergabung atau satu orang bisa terpisah.