Nadya Salsabila, . (2024) IMPLEMENTASI DEEP LEARNING UNTUK DETEKSI OBJEK POHON KELAPA SAWIT DENGAN ALGORITMA YOLO-V8. Skripsi thesis, Universitas Pembangunan Nasional Veteran Jakarta.
![[img]](http://repository.upnvj.ac.id/style/images/fileicons/text.png) |
Text
ABSTRAK.pdf Download (224kB) |
|
Text
AWAL.pdf Download (810kB) |
|
Text
BAB I.pdf Restricted to Repository UPNVJ Only Download (327kB) |
|
Text
BAB III.pdf Restricted to Repository UPNVJ Only Download (467kB) |
|
Text
BAB II.pdf Restricted to Repository UPNVJ Only Download (1MB) |
|
Text
BAB IV.pdf Restricted to Repository UPNVJ Only Download (2MB) |
|
Text
BAB V.pdf Download (310kB) |
|
Text
DAFTAR PUSTAKA.pdf Download (347kB) |
|
Text
DAFTAR RIWAYAT HIDUP.pdf Restricted to Repository UPNVJ Only Download (70kB) |
|
Text
LAMPIRAN.pdf Restricted to Repository UPNVJ Only Download (3MB) |
|
Text
HASIL PLAGIARISME.pdf Restricted to Repository staff only Download (419kB) |
|
Text
ARTIKEL KI.pdf Restricted to Repository staff only Download (1MB) |
Abstract
One of Indonesia's current industrial progress processes is the downstreaming of natural resources including downstreaming of oil palm, in line with this, the increase in oil palm production certainly has an important role. Recorded oil palm land increased in 2022 totaling 15.4 million hectares, it can be seen that there is a significant expansion of land with increased production requiring technology in plantation management so that the effectiveness and efficiency of land management is optimized. This research uses data in the form of RGB images of oil palm plantation areas from PT XYZ. Utilizing deep learning for image pre-processing, namely modifying low-resolution images into high-resolution images using the EDSR architecture and the YOLO V8 algorithm to detect oil palm tree objects. Image resolution improvement aims to optimize the input image with the EDSR architecture and the YOLO V8 algorithm used in this study includes 5 versions of YOLO V8 namely YOLO V8n, YOLO V8s, YOLO V8m, YOLO V8l and YOLO V8x with the aim of comparing the results of model accuracy in detecting objects from various model variations, for models with RGB image input, the highest accuracy results are obtained with the YOLO V8l model with a mAP value of 50 0. 92718, mAP 50-90 0.42009 and F1-Score value 0.9300, while in the input of super-resolution image data get the results of mAP 50 0.91715, mAP 50-90 0.38357, F1-Score 0.87816.
| Item Type: | Thesis (Skripsi) |
|---|---|
| Additional Information: | [No.Panggil: 1710511031] [Pembimbing: Ridwan Raafi’udin] [Penguji 1: Widya Cholil] [Penguji 2: Neny Rosmawarni] |
| Uncontrolled Keywords: | Oil palm tree, RGB Image, YOLO V8 Algorithm, EDSR |
| Subjects: | Q Science > QA Mathematics > QA75 Electronic computers. Computer science Q Science > QA Mathematics > QA76 Computer software |
| Divisions: | Fakultas Ilmu Komputer > Program Studi Informatika (S1) |
| Depositing User: | NADYA SALSABILA |
| Date Deposited: | 05 Sep 2024 02:20 |
| Last Modified: | 05 Sep 2024 02:20 |
| URI: | http://repository.upnvj.ac.id/id/eprint/31866 |
Actions (login required)
 |
View Item |