PENINGKATAN KUALITAS UNTUK DETEKSI OBJEK PADA CITRA SATELIT MENGGUNAKAN METODE SUPER RESOLUTION DAN YOLOv5

NUGRAHA, REGA SETIADI and Fachrurrozi, Muhammad and Rachmatullah, Muhammad Naufal (2024) PENINGKATAN KUALITAS UNTUK DETEKSI OBJEK PADA CITRA SATELIT MENGGUNAKAN METODE SUPER RESOLUTION DAN YOLOv5. Undergraduate thesis, Sriwijaya University.

	Text RAMA_55201_09021381924110.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (7MB) | Request a copy
	Text RAMA_55201_09021381924110_TURNITIN.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (4MB) | Request a copy
	Text RAMA_55201_09021381924110_0222058001_0001129204_01_front_ref.pdf - Accepted Version Available under License Creative Commons Public Domain Dedication. Download (1MB)
	Text RAMA_55201_09021381924110_0222058001_0001129204_02.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (4MB) | Request a copy
	Text RAMA_55201_09021381924110_0222058001_0001129204_03.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (416kB) | Request a copy
	Text RAMA_55201_09021381924110_0222058001_0001129204_04.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (1MB) | Request a copy
	Text RAMA_55201_09021381924110_0222058001_0001129204_05.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (1MB) | Request a copy
	Text RAMA_55201_09021381924110_0222058001_0001129204_06.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (114kB) | Request a copy
	Text RAMA_55201_09021381924110_0222058001_0001129204_07_ref.pdf - Bibliography Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (123kB) | Request a copy
	Text RAMA_55201_09021381924110_0222058001_0001129204_08_lamp.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (200kB) | Request a copy

Abstract

Satellite images are images or photos taken from satellites that revolve around the Earth, where the image is used in the fields of mapping, meteorology and environmental monitoring. However, there is a problem that the images produced by these satellites sometimes have low resolution and the objects in the image are not clearly visible. Therefore, to overcome these problems, an increase in resolution is needed. In this study, the increase in satellite image resolution was used with the super resolution method. Image quality improvement was carried out using a sentinel-2 satellite image dataset of 1288 data, where each data was designed with a combination of batch size and epoch parameters. From the results of data testing that has been carried out, the use of super resolution in increasing image resolution shows a significant increase in file size and image clarity. The increase occurred because the dimensional size of the image increased by 4x after the super resolution process. And the results of data testing that has been carried out between super resolution and YOLOv5 in batch 32 epoch 100 produced the best performance with a confidence score of 0.92.

Item Type:	Thesis (Undergraduate)
Uncontrolled Keywords:	Citra Satelit, Super Resolution, YOLOv5
Subjects:	Q Science > Q Science (General) > Q334-342 Computer science. Artificial intelligence. Algorithms. Robotics. Automation.
Divisions:	09-Faculty of Computer Science > 55201-Informatics (S1)
Depositing User:	Rega Setiadi Nugraha
Date Deposited:	05 Aug 2024 02:04
Last Modified:	05 Aug 2024 02:04
URI:	http://repository.unsri.ac.id/id/eprint/153933

Actions (login required)

View Item