SAFETYLIT WEEKLY UPDATE

We compile citations and summaries of about 400 new articles every week.
RSS Feed

HELP: Tutorials | FAQ
CONTACT US: Contact info

Search Results

Journal Article

Citation

Alghamdi S, van Schyndel R, Khalil I. Conf. Proc. IEEE Eng. Med. Biol. Soc. 2012; 2012: 5114-5117.

Copyright

(Copyright © 2012, IEEE (Institute of Electrical and Electronics Engineers))

DOI

10.1109/EMBC.2012.6347144

PMID

23367079

Abstract

The aim of this paper is to present a service for blind and people with low vision to assist them to cross the street independently. The presented approach provides the user with significant information such as detection of pedestrian crossing signal from any point of view, when the pedestrian crossing signal light is green, the detection of dynamic and fixed obstacles, predictions of the movement of fellow pedestrians and information on objects which may intersect his path. Our approach is based on capturing multiple frames using a depth camera which is attached to a user's headgear. Currently a testbed system is built on a helmet and is connected to a laptop in the user's backpack. In this paper, we discussed efficiency of using Speeded-Up Robust Features (SURF) algorithm for object recognition for purposes of blind people assistance. The system predicts the movement of objects of interest to provide the user with information on the safest path to navigate and information on the surrounding area. Evaluation of this approach on real sequence video frames provides 90% of human detection and more than 80% for recognition of other related objects.


Language: en

NEW SEARCH


All SafetyLit records are available for automatic download to Zotero & Mendeley
Print