Image of IDENTIFIKASI KENDARAAN DENGAN MENGGUNAKAN YOLO DAN UNTUK MENENTUKAN KEPADATAN KENDARAAN DI JALAN PROTOKOL KOTA PALEMBANG MENGGUNAKAN ALGORITMA CONVOLUTIONAL NEURAL NETWORK (CNN)

Skripsi

IDENTIFIKASI KENDARAAN DENGAN MENGGUNAKAN YOLO DAN UNTUK MENENTUKAN KEPADATAN KENDARAAN DI JALAN PROTOKOL KOTA PALEMBANG MENGGUNAKAN ALGORITMA CONVOLUTIONAL NEURAL NETWORK (CNN)

Penilaian

0,0

dari 5
Penilaian anda saat ini :  

The increasing volume of vehicles each year results in an escalating daily traffic volume, leading to issues such as congestion and vehicle density that adversely affect various sectors. Therefore, this research aims to develop a vehicle detection system and vehicle count using the You Only Look Once (YOLO) generation 8 algorithm, assisted by the DeepSort architecture, to count the number of vehicles crossing a Counter line. In addition to object detection, this research study also focuses on using Convolutional Neural Network (CNN) methods to determine road conditions, whether they are considered smooth, moderate, or congested. To support this research study, a dataset consisting of 3592 image files and 72 video files containing information about vehicles such as motorcycles and cars was used. However, for the dataset model used in this research study, there are five variables: motorcycles, cars, red lights, green lights, and zebra crossings. From the image dataset, a YOLOv8 model was obtained with a training accuracy of 93.73% and a testing accuracy of 93.73%. The accuracy of the YOLOv8 model already demonstrates excellent performance in detecting vehicle objects. During the creation of the CNN model, an accuracy of 94.27% was achieved, and when testing the output video results in the form of a CSV file, it can be concluded that Monday mornings tend to be congested, Wednesdays are relatively smooth, Fridays have moderate road conditions on average, and Saturdays also have moderate conditions on average. Interestingly, on Mondays, Wednesdays, Fridays, or Saturdays, in the afternoon, the road conditions in Palembang city are always moderate.

Availability
Inventory Code Barcode Call Number Location Status
2407000271T137898T1378982024Central Library (Referens)Available but not for loan - Not for Loan
Detail Information
Series Title
-
Call Number
T1378982024
Publisher
Inderalaya : Prodi Sistem Komputer, Fakultas Ilmu Komputer Uniersitas Sriwijaya.,
Collation
xiv, 70 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
Other version/related

No other version available

File Attachment
Comments
You must be logged in to post a comment