Deteksi Tipe Mobil Menggunakan YOLOv5

Ferdiansyah, Fahrul Ihza (2025) Deteksi Tipe Mobil Menggunakan YOLOv5. Other thesis, Institut Teknologi Sepuluh November.

Text 07211740000046-Undergraduate_Thesis.pdf - Accepted Version Restricted to Repository staff only Download (13MB) | Request a copy

Abstract

Pengenalan visual mobil secara otomatis merupakan tantangan utama dalam visi komputer
dan pemrosesan citra. Metode yang efektif dan efisien diperlukan untuk mendeteksi dan mengk
lasifikasikan tipe mobil dalam berbagai konteks, seperti keamanan jalan raya, dan analisis lalu
lintas. YOLOv5, sebuah model deteksi objek berbasis deep learning, telah menunjukkan kinerja
yang mengesankan dalam memecahkan masalah ini. Penelitian ini mengeksplorasi penerapan
YOLOv5 dalam mendeteksi tipe mobil secara real-time dari video atau gambar, dengan fokus
pada presisi, kecepatan, dan skalabilitas. Pendekatan ini mencakup proses pelatihan model,
tuning parameter, dan evaluasi kinerja menggunakan dataset yang relevan. Hasil eksperimen
menunjukkan bahwa YOLOv5 mampu mencapai tingkat akurasi yang tinggi dalam mendeteksi
berbagai tipe mobil dengan waktu respons yang cepat, memvalidasi potensi besar teknologi ini
dalam aplikasi keamanan dan pemantauan di masa depan.
====================================================================================================================================================================================
Automated visual recognition of cars poses a significant challenge in computer vision and
image processing. Effective and efficient methods are required to detect and classify car types
across various contexts such as road safety, and traffic analysis. YOLOv5, a deep learning
based object detection model, has demonstrated impressive performance in addressing this
problem. This research explores the application of YOLOv5 for real-time detection of car types
from video or images, emphasizing precision, speed, and scalability. The approach covers
model training, parameter tuning, and performance evaluation using relevant datasets. Exper
imental results show that YOLOv5 achieves high accuracy in detecting various car types with
fast response

Item Type:	Thesis (Other)
Uncontrolled Keywords:	Mobil, Deteksi, YOLOv5, Car, YOLOv5, Detection
Subjects:	T Technology > TA Engineering (General). Civil engineering (General) > TA1637 Image processing--Digital techniques. Image analysis--Data processing.
Divisions:	Faculty of Intelligent Electrical and Informatics Technology (ELECTICS) > Computer Engineering > 90243-(S1) Undergraduate Thesis
Depositing User:	Fahrul Ihza Ferdiansyah
Date Deposited:	04 Aug 2025 07:56
Last Modified:	04 Aug 2025 07:56
URI:	http://repository.its.ac.id/id/eprint/123969

Actions (login required)

View Item