Skripsi

DETEKSI PELANGGARAN KENDARAAN PADA ZEBRA CROSS MENGGUNAKAN SUPERVISION DAN PENENTUAN TINGKAT PELANGGARAN MENGGUNAKAN ALGORITMA TWO DIMENSIONAL CONVOLUTIONAL NEURAL NETWORK PADA JALAN RAYA KOTA PALEMBANG

---

Penilaian

---

In this study, the You Only Look Once Version 8 (YOLOv8) algorithm was used to detect and use the Supervision library to calculate the number of vehicles violating zebra crossings. The Two Dimensional Convolutional Neural Network (2DCNN) method was used to determine the level of violations with the parameters zero, low, medium, and high. This research uses a vehicle image dataset totaling 3592 images. YOLOv8 in this study produced an mAP model of 85.8% and YOLOv8 testing accuracy with Supervision of 94.39% through comparison of model detection results and manual calculation results. Furthermore, the 2DCNN method produces model training accuracy of 93% and testing accuracy of 98% and produces a low average violation rate on data consisting of 23 videos originating from three traffic intersections in the city of Palembang.

---

Availability

Inventory Code	Barcode	Call Number	Location	Status
2407001452	T137827	T1378272024	Central Library (Referens)	Available but not for loan - Not for Loan

Detail Information

Series Title

-

Call Number

T1378272024

Publisher

Inderalaya : Prodi Sistem Komputer, Fakultas Ilmu Komputer Uniersitas Sriwijaya., 2024

Collation

xvi, 84 hlm.; Ilus.; 29 cm

Language

Indonesia

ISBN/ISSN

-

Classification

006.307

Content Type

Text

Media Type

unmediated

Carrier Type

-

Edition

-

Subject(s)

Sistem Pakar
Prodi Sistem Komputer

Specific Detail Info

-

Statement of Responsibility

SEPTA

Other version/related

File Attachment

Comments

---

You must be logged in to post a comment