UNIGE document Chapitre d'actes
previous document  unige:74463  next document
add to browser collection

An Embedded Ground Change Detector for a "Smart Walker"

Published in Artificial Computation in Biology and Medicine. Elche, Spain - June 1-5, 2015 - Springer. 2015, p. 533-542
Collection Lecture Notes in Computer Science; 9107
Abstract Millions of elderly people around the world use the walker for their mobility; nevertheless, these devices may lead to an accident. One of the cause of these accidents is misjudge the terrain. The main objective of this work is the implementation of a ground change detector in real time on a small and light embedded system that can be clipped on a rollator. As a long-term goal, this device will allow users to anticipate entering dangerous situations. We implemented an algorithm to detect ground changes based on color histograms and texture descriptor given as inputs to multi-layer perceptrons. Experiments were performed both off-line and with an embedded system. The obtained results indicated that it is possible to have an accurate detector which is able to distinguish ground changes in real-time.
Keywords Ground change detectorEmbedded systemArtificial Neural Network (ANN)Elderly careGerontechnology
ISBN: 978-3-319-18913-0
Full text
Proceedings (Accepted version) (2.6 MB) - public document Free access
Research groups Computer Vision and Multimedia Laboratory
Multimodal Interaction Group
(ISO format)
WEISS VELANDIA, Viviana Lucia et al. An Embedded Ground Change Detector for a "Smart Walker". In: Artificial Computation in Biology and Medicine. Elche, Spain. [s.l.] : Springer, 2015. p. 533-542. (Lecture Notes in Computer Science; 9107) doi: 10.1007/978-3-319-18914-7_56 https://archive-ouverte.unige.ch/unige:74463

603 hits



Deposited on : 2015-08-04

Export document
Format :
Citation style :