Article Per Year (5 Year)
p-Index From 2019 - 2024
0
P-Index
This Author published in this journals
All Journal Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer
Achmad Jafar Al Kadafi
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 
Deteksi Objek Penghalang Secara Real-Time Berbasis Mobile Bagi Penyandang Tunanetra Menggunakan Analisis Blob Achmad Jafar Al Kadafi; Fitri Utaminingrum
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 2 No 1 (2018): Januari 2018
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (1214.552 KB)

Abstract

Blind is a condition when the visual sense experiencing interference or obstacles, so requiring an aids like stick to walking. But, the using of stick does not help them much in walk especially to detect obstacles. In Computer Vision science so possible for people with the visual impairment can do an activity like normal people in general. In computer vision science is so possible for people with visual impairment can do walking activities like a normal people in general. Therefore, this research built a system based computer vision that is applied to a mobile device to detect obstacles on real-time when the visual impairment person walks indoors. Mobile devices will be conditioned at a height of 1 meter above the floor and angle between 52 o to 62 o to get a distance of about 2 meters in front of the user. In general, the obstruction detection process built by applying the Connected Component Labeling method to get a blob from the image. To support the detection process, segmentation process is done using threshold method by utilizing RGB normalization color model based on the dominant bright of floor color. The threshold value used is based on the minimum and maximum values ​​of each component of RGB normalization. Test results shows that the system is able to detect obstacles with an accuracy of 81.25%.
Co-Authors Utaminingrum, Fitri