UNIGE document Conference Proceedings
previous document  unige:74461  next document
add to browser collection
Title

A robust, real-time ground change detector for a "smart" walker

Authors
Hasler, David
Year 2014
Abstract Nowadays, there are many different types of mobility aids for elderly people. Nevertheless, these devices may lead to accidents, depending on the terrain where they are being used. In this context, the goal of the EyeWalker project is to develop a ultralight computer vision device for users with mobility problems. One of the main objective of this work is to develop a ground change detection module that will warn the user before entering dangerous terrains or hostile situations. This software component integrated on a ”smart” walker will be able to react in real time, to operate both indoor and outdoor, as well as in familiar or unfamiliar environments. Specifically, we propose a classification algorithm using colour and texture as a descriptor to detect ground changes. In our classifier, the distributions of HSV colours and Local Edge Patterns are used to compare the similarity between the current frame and the average of the k previous frames. To compare similarities, we used four different techniques (Histogram Intersection, Kolmogorov-Smirnov, Cumulative Integral and Artificial Neural Networks) with outdoor training images. Preliminary results reveal that artificial neural networks achieved the best performances.
Keywords Ground change detectionHSV colour modelLocal Edge Patter (LEP)Elderly careGerontechnology
Full text
Proceedings (Author postprint) (11.1 MB) - public document Free access
Structures
Research groups Computer Vision and Multimedia Laboratory
Multimodal Interaction Group
Citation
(ISO format)
WEISS VELANDIA, Viviana Lucia et al. A robust, real-time ground change detector for a "smart" walker. [s.l.] : [s.n.], 2014. https://archive-ouverte.unige.ch/unige:74461

240 hits

52 downloads

Update

Deposited on : 2015-08-04

Export document
Format :
Citation style :