An enhanced obstacle avoidance method for the visually impaired using deformable grid

Mun Cheon Kang, Sung Ho Chae, Jee Young Sun, Sung Ho Lee, Sung-Jea Ko

Research output: Contribution to journalArticle

9 Citations (Scopus)

Abstract

Various obstacle avoidance (OA) methods with the monocular vision have been studied to assist visually impaired people. Recently, a method that effectively locates obstacles at a risk of collision using the shape variation of a grid, called deformable grid (DG), was introduced [11]. To further improve the detection performance of the previous work, a vertex deformation function representing the displacement of each vertex in the DG is firstly defined employing the perspective projection geometry. Then, the collision risk is accurately estimated based on the shape variation of the DG that is measured using the vertex deformation function. Experimental results show that the proposed method outperforms other conventional methods as well as the previous work in terms of both the accuracy and processing time, and clearly detects obstacles that present a risk of collision in a variety of scenarios. This method is suitable for application to electronic travel aid (ETA) systems using consumer devices, such as smart-phones, tablets, and wearable devices.

Original languageEnglish
Article number8013256
Pages (from-to)169-177
Number of pages9
JournalIEEE Transactions on Consumer Electronics
Volume63
Issue number2
DOIs
Publication statusPublished - 2017 May 1

Fingerprint

Collision avoidance
Geometry
Processing

Keywords

  • collision avoidance
  • Electronic Travel Aids (ETA)
  • Obstacle avoidance
  • obstacle detection
  • visually impaired

ASJC Scopus subject areas

  • Media Technology
  • Electrical and Electronic Engineering

Cite this

An enhanced obstacle avoidance method for the visually impaired using deformable grid. / Kang, Mun Cheon; Chae, Sung Ho; Sun, Jee Young; Lee, Sung Ho; Ko, Sung-Jea.

In: IEEE Transactions on Consumer Electronics, Vol. 63, No. 2, 8013256, 01.05.2017, p. 169-177.

Research output: Contribution to journalArticle

Kang, Mun Cheon ; Chae, Sung Ho ; Sun, Jee Young ; Lee, Sung Ho ; Ko, Sung-Jea. / An enhanced obstacle avoidance method for the visually impaired using deformable grid. In: IEEE Transactions on Consumer Electronics. 2017 ; Vol. 63, No. 2. pp. 169-177.
@article{a7db75fa379e47219ad06542cc76f44a,
title = "An enhanced obstacle avoidance method for the visually impaired using deformable grid",
abstract = "Various obstacle avoidance (OA) methods with the monocular vision have been studied to assist visually impaired people. Recently, a method that effectively locates obstacles at a risk of collision using the shape variation of a grid, called deformable grid (DG), was introduced [11]. To further improve the detection performance of the previous work, a vertex deformation function representing the displacement of each vertex in the DG is firstly defined employing the perspective projection geometry. Then, the collision risk is accurately estimated based on the shape variation of the DG that is measured using the vertex deformation function. Experimental results show that the proposed method outperforms other conventional methods as well as the previous work in terms of both the accuracy and processing time, and clearly detects obstacles that present a risk of collision in a variety of scenarios. This method is suitable for application to electronic travel aid (ETA) systems using consumer devices, such as smart-phones, tablets, and wearable devices.",
keywords = "collision avoidance, Electronic Travel Aids (ETA), Obstacle avoidance, obstacle detection, visually impaired",
author = "Kang, {Mun Cheon} and Chae, {Sung Ho} and Sun, {Jee Young} and Lee, {Sung Ho} and Sung-Jea Ko",
year = "2017",
month = "5",
day = "1",
doi = "10.1109/TCE.2017.014832",
language = "English",
volume = "63",
pages = "169--177",
journal = "IEEE Transactions on Consumer Electronics",
issn = "0098-3063",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "2",

}

TY - JOUR

T1 - An enhanced obstacle avoidance method for the visually impaired using deformable grid

AU - Kang, Mun Cheon

AU - Chae, Sung Ho

AU - Sun, Jee Young

AU - Lee, Sung Ho

AU - Ko, Sung-Jea

PY - 2017/5/1

Y1 - 2017/5/1

N2 - Various obstacle avoidance (OA) methods with the monocular vision have been studied to assist visually impaired people. Recently, a method that effectively locates obstacles at a risk of collision using the shape variation of a grid, called deformable grid (DG), was introduced [11]. To further improve the detection performance of the previous work, a vertex deformation function representing the displacement of each vertex in the DG is firstly defined employing the perspective projection geometry. Then, the collision risk is accurately estimated based on the shape variation of the DG that is measured using the vertex deformation function. Experimental results show that the proposed method outperforms other conventional methods as well as the previous work in terms of both the accuracy and processing time, and clearly detects obstacles that present a risk of collision in a variety of scenarios. This method is suitable for application to electronic travel aid (ETA) systems using consumer devices, such as smart-phones, tablets, and wearable devices.

AB - Various obstacle avoidance (OA) methods with the monocular vision have been studied to assist visually impaired people. Recently, a method that effectively locates obstacles at a risk of collision using the shape variation of a grid, called deformable grid (DG), was introduced [11]. To further improve the detection performance of the previous work, a vertex deformation function representing the displacement of each vertex in the DG is firstly defined employing the perspective projection geometry. Then, the collision risk is accurately estimated based on the shape variation of the DG that is measured using the vertex deformation function. Experimental results show that the proposed method outperforms other conventional methods as well as the previous work in terms of both the accuracy and processing time, and clearly detects obstacles that present a risk of collision in a variety of scenarios. This method is suitable for application to electronic travel aid (ETA) systems using consumer devices, such as smart-phones, tablets, and wearable devices.

KW - collision avoidance

KW - Electronic Travel Aids (ETA)

KW - Obstacle avoidance

KW - obstacle detection

KW - visually impaired

UR - http://www.scopus.com/inward/record.url?scp=85028949850&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85028949850&partnerID=8YFLogxK

U2 - 10.1109/TCE.2017.014832

DO - 10.1109/TCE.2017.014832

M3 - Article

VL - 63

SP - 169

EP - 177

JO - IEEE Transactions on Consumer Electronics

JF - IEEE Transactions on Consumer Electronics

SN - 0098-3063

IS - 2

M1 - 8013256

ER -