Collision detection based on scale change of image segments for the visually impaired

Sung Ho Chae, Jee Young Sun, Mun Cheon Kang, Byoung Jun Son, Sung-Jea Ko

Research output: Chapter in Book/Report/Conference proceedingConference contribution

4 Citations (Scopus)

Abstract

A variety of portable or wearable navigation systems mounted on smart glasses and smartphones have been developed to assist visually impaired people over the last decade. In these systems, collision detection is one of the key components. Many conventional methods with the monocular vision estimate the collision risk based on the motion information of obstacles in the image by measuring the size change of objects using detected feature points and their corresponding motion vectors. However, the size change is sometimes incorrectly measured due to unreliable feature points and motion vectors. To overcome this problem, we present a motion clustering scheme to remove outliers among both feature points and motion vectors. Experimental results indicate that the proposed collision detection method outperforms the conventional one in terms of detection and false positive rates.

Original languageEnglish
Title of host publication2015 IEEE International Conference on Consumer Electronics, ICCE 2015
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages511-512
Number of pages2
ISBN (Print)9781479975426
DOIs
Publication statusPublished - 2015 Mar 23
Event2015 IEEE International Conference on Consumer Electronics, ICCE 2015 - Las Vegas, United States
Duration: 2015 Jan 92015 Jan 12

Other

Other2015 IEEE International Conference on Consumer Electronics, ICCE 2015
CountryUnited States
CityLas Vegas
Period15/1/915/1/12

Fingerprint

Smartphones
Navigation systems
Glass

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Electrical and Electronic Engineering
  • Industrial and Manufacturing Engineering

Cite this

Chae, S. H., Sun, J. Y., Kang, M. C., Son, B. J., & Ko, S-J. (2015). Collision detection based on scale change of image segments for the visually impaired. In 2015 IEEE International Conference on Consumer Electronics, ICCE 2015 (pp. 511-512). [7066504] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICCE.2015.7066504

Collision detection based on scale change of image segments for the visually impaired. / Chae, Sung Ho; Sun, Jee Young; Kang, Mun Cheon; Son, Byoung Jun; Ko, Sung-Jea.

2015 IEEE International Conference on Consumer Electronics, ICCE 2015. Institute of Electrical and Electronics Engineers Inc., 2015. p. 511-512 7066504.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Chae, SH, Sun, JY, Kang, MC, Son, BJ & Ko, S-J 2015, Collision detection based on scale change of image segments for the visually impaired. in 2015 IEEE International Conference on Consumer Electronics, ICCE 2015., 7066504, Institute of Electrical and Electronics Engineers Inc., pp. 511-512, 2015 IEEE International Conference on Consumer Electronics, ICCE 2015, Las Vegas, United States, 15/1/9. https://doi.org/10.1109/ICCE.2015.7066504
Chae SH, Sun JY, Kang MC, Son BJ, Ko S-J. Collision detection based on scale change of image segments for the visually impaired. In 2015 IEEE International Conference on Consumer Electronics, ICCE 2015. Institute of Electrical and Electronics Engineers Inc. 2015. p. 511-512. 7066504 https://doi.org/10.1109/ICCE.2015.7066504
Chae, Sung Ho ; Sun, Jee Young ; Kang, Mun Cheon ; Son, Byoung Jun ; Ko, Sung-Jea. / Collision detection based on scale change of image segments for the visually impaired. 2015 IEEE International Conference on Consumer Electronics, ICCE 2015. Institute of Electrical and Electronics Engineers Inc., 2015. pp. 511-512
@inproceedings{0f38c1523da3494db298ddda104b3491,
title = "Collision detection based on scale change of image segments for the visually impaired",
abstract = "A variety of portable or wearable navigation systems mounted on smart glasses and smartphones have been developed to assist visually impaired people over the last decade. In these systems, collision detection is one of the key components. Many conventional methods with the monocular vision estimate the collision risk based on the motion information of obstacles in the image by measuring the size change of objects using detected feature points and their corresponding motion vectors. However, the size change is sometimes incorrectly measured due to unreliable feature points and motion vectors. To overcome this problem, we present a motion clustering scheme to remove outliers among both feature points and motion vectors. Experimental results indicate that the proposed collision detection method outperforms the conventional one in terms of detection and false positive rates.",
author = "Chae, {Sung Ho} and Sun, {Jee Young} and Kang, {Mun Cheon} and Son, {Byoung Jun} and Sung-Jea Ko",
year = "2015",
month = "3",
day = "23",
doi = "10.1109/ICCE.2015.7066504",
language = "English",
isbn = "9781479975426",
pages = "511--512",
booktitle = "2015 IEEE International Conference on Consumer Electronics, ICCE 2015",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Collision detection based on scale change of image segments for the visually impaired

AU - Chae, Sung Ho

AU - Sun, Jee Young

AU - Kang, Mun Cheon

AU - Son, Byoung Jun

AU - Ko, Sung-Jea

PY - 2015/3/23

Y1 - 2015/3/23

N2 - A variety of portable or wearable navigation systems mounted on smart glasses and smartphones have been developed to assist visually impaired people over the last decade. In these systems, collision detection is one of the key components. Many conventional methods with the monocular vision estimate the collision risk based on the motion information of obstacles in the image by measuring the size change of objects using detected feature points and their corresponding motion vectors. However, the size change is sometimes incorrectly measured due to unreliable feature points and motion vectors. To overcome this problem, we present a motion clustering scheme to remove outliers among both feature points and motion vectors. Experimental results indicate that the proposed collision detection method outperforms the conventional one in terms of detection and false positive rates.

AB - A variety of portable or wearable navigation systems mounted on smart glasses and smartphones have been developed to assist visually impaired people over the last decade. In these systems, collision detection is one of the key components. Many conventional methods with the monocular vision estimate the collision risk based on the motion information of obstacles in the image by measuring the size change of objects using detected feature points and their corresponding motion vectors. However, the size change is sometimes incorrectly measured due to unreliable feature points and motion vectors. To overcome this problem, we present a motion clustering scheme to remove outliers among both feature points and motion vectors. Experimental results indicate that the proposed collision detection method outperforms the conventional one in terms of detection and false positive rates.

UR - http://www.scopus.com/inward/record.url?scp=84936086363&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84936086363&partnerID=8YFLogxK

U2 - 10.1109/ICCE.2015.7066504

DO - 10.1109/ICCE.2015.7066504

M3 - Conference contribution

AN - SCOPUS:84936086363

SN - 9781479975426

SP - 511

EP - 512

BT - 2015 IEEE International Conference on Consumer Electronics, ICCE 2015

PB - Institute of Electrical and Electronics Engineers Inc.

ER -