Please use this identifier to cite or link to this item: https://repository.uksw.edu//handle/123456789/34883
Title: Identifikasi Kendaraan Beroda Menggunakan Algoritma Yolov5
Other Titles: Wheeled Vehicle Identification Using YOLOv5 Algorithm
Authors: .Michael, Michael
Keywords: Kepadatan lalu lintas;Deteksi objek;YOLO (You Only Look Once);Deteksi kendaraan
Issue Date: 29-May-2024
Abstract: Pentingnya pengukuran kepadatan lalu lintas dalam perencanaan jalan memunculkan upaya otomatisasi menggunakan algoritma deteksi objek, terutama YOLO (You Only Look Once), yang menggantikan proses manual yang rawan kesalahan dan memakan waktu. Meski demikian, tantangan muncul saat lalu lintas padat, menantang akurasi deteksi kendaraan. Dalam rangka mengatasi kendala ini, penelitian ini bertujuan membandingkan performa deteksi kendaraan antara dua pendekatan YOLO: deteksi lapisan multi-view dan deteksi konvensional, dengan fokus pada YOLOv5n, YOLOv5s, YOLOv5m, dan YOLOv5l. Kajian literatur melibatkan bidang Computer Vision, implementasi YOLO, dan riset terkait guna memberikan konteks konseptual. Metode penelitian mendetailkan langkah-langkah identifikasi kendaraan dengan YOLOv5, dan evaluasi hasilnya mencakup performa berbagai varian YOLO dan pendekatan deteksi multi-view. Dengan demikian, melalui penelitian ini, diharapkan akan diperoleh wawasan yang lebih mendalam untuk membangun model yang efektif serta memudahkan pemilihan model YOLO yang sesuai untuk deteksi kendaraan.
The importance of traffic density measurement in road planning has led to efforts in automation using object detection algorithms, particularly YOLO (You Only Look Once), replacing error-prone and time-consuming manual processes. However, challenges arise in dense traffic conditions, posing a challenge to vehicle detection accuracy. This research aims to compare the performance of vehicle detection between two YOLO approaches: multi-view layer detection and conventional detection, focusing on YOLOv5n, YOLOv5s, and YOLOv5m. The literature review encompasses Computer Vision, YOLO implementation, and related research to provide conceptual context. The research method details the steps of vehicle identification using YOLOv5, and the evaluation includes the performance of various YOLO variants and multi-view detection approaches. Thus, this study, is expected to gain deeper insights into building an effective model and facilitating the selection of a suitable YOLO model for vehicle detection.
URI: https://repository.uksw.edu//handle/123456789/34883
Appears in Collections:T1 - Informatics Engineering

Files in This Item:
File Description SizeFormat 
T1_672020033_Judul.pdf330.47 kBAdobe PDFView/Open
T1_672020033_Isi.pdf
  Until 9999-01-01
819.66 kBAdobe PDFView/Open
T1_672020033_Daftar Pustaka.pdf235 kBAdobe PDFView/Open
T1_672020033_Lampiran.pdf
  Until 9999-01-01
349.55 kBAdobe PDFView/Open
T1_672020033_Formulir Pernyataan Persetujuan Penyerahan Lisensi dan Pilihan Embargo.pdf
  Until 9999-01-01
1.06 MBAdobe PDFView/Open


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.