Home > Archive > 2020 > Volume 10 Number 3 (May 2020) >
IJMLC 2020 Vol.10(3): 495-500 ISSN: 2010-3700
DOI: 10.18178/ijmlc.2020.10.3.963

Obstacle Height Estimation Related to Suitable Viewpoint while Waiting for the Bus Using Color Moment Technique

Watcharin Tangsuksant and Chikamune Wada

Abstract—To achieve the final goal of assisting blind people with obstacle detection along the roadside, the estimated height of obstacles is a crucial part of our proposed system, which is particularly important when waiting at bus stops. The color moment technique is used for matching the obstacle areas between two image areas. However, to distinguish between matching and non-matching images, it is necessary to establish certain criteria. This research proposes criteria selection and optimization based on different weight values used in a color moment equation and distance error measurement. Moreover, HSV and RGB color models were compared. The experimental results indicated that the optimal performance of the color moment technique with a weight of (3, 1, 1) resulted in an accuracy up to 86% for the RGB color model. This high level of performance strongly suggests that our assistive application for blind people would be both feasible and beneficial.

Index Terms—Assistive application for blind, bus-waiting color moment, height of obstacle estimation, suitable viewpoints.

Watcharin Tangsuksant and Chikamune Wada are with the Graduate School of Life Science and Systems Engineering, Kyushu Institute of Technology, Hibikino 2-4 Wakamatsu-ku Kitakyushu, Fukuoka 808-0196, Japan (e-mail: w.tangsuksant.m@hotmail.com, wada@brain.kyutech.ac.jp).

[PDF]

Cite: Watcharin Tangsuksant and Chikamune Wada, "Obstacle Height Estimation Related to Suitable Viewpoint while Waiting for the Bus Using Color Moment Technique," International Journal of Machine Learning and Computing vol. 10, no. 3, pp. 495-500, 2020.

Copyright © 2020 by the authors. This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited (CC BY 4.0).

General Information

  • ISSN: 2010-3700 (Online)
  • Abbreviated Title: Int. J. Mach. Learn. Comput.
  • Frequency: Bimonthly
  • DOI: 10.18178/IJMLC
  • Editor-in-Chief: Dr. Lin Huang
  • Executive Editor:  Ms. Cherry L. Chen
  • Abstracing/Indexing: Inspec (IET), Google Scholar, Crossref, ProQuest, Electronic Journals Library.
  • E-mail: ijmlc@ejournal.net


Article Metrics