Skripsi

SIMULASI DETEKSI PELANGGARAN PENGGUNAAN HELM DAN KECEPATAN KENDARAAN MENGGUNAKAN ALGORITMA CNN PADA REKAMAN KAMERA DI JALAN PROTOKOL

---

This research will focus on developing and testing a helmet violation and vehicle speed detection system based on the YOLO algorithm and classification using a Convolutional Neural Network (CNN). The purpose of writing this thesis is to implement the YOLOv8 algorithm for Detecting Helmet Violations and Vehicle Speed, calculating the accuracy level of the detection system using You Only Look Once (YOLO)v8 in detecting helmet violations and vehicle speed, and classifying the Level of Traffic Violations Using Convolutional Neural Network (CNN). From the data training process, a total accuracy of 83% was obtained, which means the resulting model was quite good. The model succeeded in detecting class 0, namely "Motorcycles using helmets" with an accuracy of 78.05%, class 1, namely "Cars" with an accuracy of 83.54%, and class 1 "Motorcycles not using helmets" with an accuracy of 89.77%. The area with the highest level of violations is the new boom area, namely 6 of the 11 categories predicted to be high by CNN.

---

Availability

Detail Information

Series Title

-

Call Number

T1520552024

Publisher

Indralaya : Prodi Sistem Komputer, Fakultas Ilmu Komputer Universitas Sriwijaya., 2024

Collation

xii, 75 hlm.; ilus.; 29 cm

Language

Indonesia

ISBN/ISSN

-

Classification

006.370 7

Content Type

Text

Media Type

unmediated

Carrier Type

-

Edition

-

Subject(s)

Prodi Sistem Komputer
Convolutional Neural Network (CNN)

Specific Detail Info

-

Statement of Responsibility

KA

Other version/related

File Attachment

Comments

---

You must be logged in to post a comment