Article Per Year (5 Year)
p-Index From 2019 - 2024
0.23
P-Index
This Author published in this journals
All Journal Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer
Lilo Nofrizal Akbar
Fakultas Ilmu Komputer, Universitas Brawijaya
Computer Science & IT Control & Systems Engineering Education Electrical & Electronics Engineering Engineering

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

 1 
Klasifikasi Golongan Kendaraan Berdasarkan Fitur Histogram of Oriented Gradients (HOG) Menggunakan metode K-Nearest Neighbors (K-NN) Berbasis Raspberry PI 3 Lilo Nofrizal Akbar; Fitri Utaminingrum
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 3 No 9 (2019): September 2019
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (836.759 KB)

Abstract

The queues that occur when making toll road payments are still a problem in Indonesia, one of which is the problem because there is no system that automatically classifies vehicles passing on the toll road, so that large vehicles such as trucks that are divided into 5 classes must be manually differentiated by toll gate officers. One effort to overcome these problems, in this study a system was designed to be able to automatically classify vehicles passing the toll road into 5 classes according to the class applicable to the Indonesian toll road, so the classification process that was previously done manually can be done automatically, this of course bring benefits to the payment transaction time for each vehicle that is getting shorter, which in turn can reduce the potential for congestion that occurs at the toll gate. This system works based on image processing, the classification process begins with vehicle video capture using a webcam, then the vehicle video is processed on Raspberry Pi 3 to extract image features from the vehicle using the Histogram of Oriented Gradients (HOG) method, then the features obtained are processed The classification uses the k-Nearest Neighbors (k-NN) method to determine the class of vehicle, then results of the classification are displayed on the LCD screen. From the tests conducted on the system using 25 test data, with each class as many as 5 test data, the results obtained for system accuracy in class 1 by 80%, class 2 by 80%, class 3 by 60%, class 4 by 60%, and class 5 by 60% .
Co-Authors Utaminingrum, Fitri