Markerless localization for blind users using computer vision and particle swarm optimization

Authors:
Hashem Tamimi;Anas Sharabati
Affiliations:
Information Technology Department, College of Administrative Sciences and Informatics, Palestine Polytechnic University, Hebron, Palestine;Information Technology Department, College of Administrative Sciences and Informatics, Palestine Polytechnic University, Hebron, Palestine
Venue:
EvoApplicatons'10 Proceedings of the 2010 international conference on Applications of Evolutionary Computation - Volume Part I
Year:
2010

Citing 5
Cited 0

Histogram refinement for content-based image retrieval

WACV '96 Proceedings of the 3rd IEEE Workshop on Applications of Computer Vision (WACV '96)
Distinctive Image Features from Scale-Invariant Keypoints

International Journal of Computer Vision
Interactive tracking of movable objects for the blind on the basis of environment models and perception-oriented object recognition methods

Proceedings of the 8th international ACM SIGACCESS conference on Computers and accessibility
A Dynamic Swarm for Visual Location Tracking

ANTS '08 Proceedings of the 6th international conference on Ant Colony Optimization and Swarm Intelligence
Human detection using oriented histograms of flow and appearance

ECCV'06 Proceedings of the 9th European conference on Computer Vision - Volume Part II

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper, we propose a novel approach, which aims to solve the localization and target-finding problem for blind and partially sighted people. A guidance system, solely implemented on a mobile phone with a camera, is employed. A computer vision approach integrated with Particle Swarm Optimization (PSO) is proposed for tracking the location. Using PSO leads to many advantages: first, it is possible to obtain robust localization results by combining the current and historical information about the location of the blind person. Second, it helps the system to resolve from ambiguous situations caused by facing similar images at different locations. Third, it can detect and recover from cases where the calculated location is wrong. Experimental results show that the proposed method works efficiently because of the simplicity of the approach, which makes it suitable for mobile applications.