An Obstacle Categorization System for Visually Impaired People

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

In this paper, we introduce a new framework for obstacle localization and classification. The proposed method is designed to improve cognition of visually impaired people (VI) facilitating the autonomous navigation in outdoor environments. In the context of computer vision applications, the following contributions are proposed and validated: (i) a new method of selecting a reduced and relevant set of interest points, (ii) a novel descriptor denoted Adaptive Histogram of Oriented Gradients (A-HOG) dedicated to arbitrary categories of objects, (iii) an image re-ranking method at Vector of Locally Aggregated Descriptor (VLAD) /Bag of Visual Word (BoVW) descriptor level based on graph spanning structures and neighborhood relations. Finally, we demonstrate the performance of the proposed framework (in terms of classification accuracy and computational time) on a challenging video dataset captured with the help of real VI users. The entire framework is completely integrated on an Android smartphone device, while all methods were specifically designed and tuned under the constraint of achieving real-time processing capabilities.

Original languageEnglish
Title of host publicationProceedings - 11th International Conference on Signal-Image Technology and Internet-Based Systems, SITIS 2015
EditorsKokou Yetongnon, Albert Dipanda, Richard Chbeir
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages147-154
Number of pages8
ISBN (Electronic)9781467397216
DOIs
Publication statusPublished - 5 Feb 2016
Externally publishedYes
Event11th International Conference on Signal-Image Technology and Internet-Based Systems, SITIS 2015 - Bangkok, Thailand
Duration: 23 Nov 201527 Nov 2015

Publication series

NameProceedings - 11th International Conference on Signal-Image Technology and Internet-Based Systems, SITIS 2015

Conference

Conference11th International Conference on Signal-Image Technology and Internet-Based Systems, SITIS 2015
Country/TerritoryThailand
CityBangkok
Period23/11/1527/11/15

Keywords

  • A-HOG descriptor
  • BoVW
  • VLAD
  • image re-ranking
  • relevant interest points

Fingerprint

Dive into the research topics of 'An Obstacle Categorization System for Visually Impaired People'. Together they form a unique fingerprint.

Cite this