Descending stairs detection with low-power sensors

Cloix, Séverine (CSEM SA, Neuchâtel, Switzerland ; Computer Science Department, University of Geneva, Geneva, Switzerland) ; Bologna, Guido (Computer Science Department, University of Geneva, Geneva, Switzerland) ; Weiss, Viviana (Computer Science Department, University of Geneva, Geneva, Switzerland) ; Pun, Thierry (Computer Science Department, University of Geneva, Geneva, Switzerland) ; Hasler, David (CSEM SA, Neuchâtel, Switzerland)

With the increasing proportion of senior citizens, many mobility aid devices were developed such as the rollator. However among walker’s users, 87% of their falls is attributed to rollators. The EyeWalker project aims at developing a small device for rollators to protect elderly people from such dangers. Descending stairs are ones of the potential hazards rollator users have to daily face. We propose a method to detect them in real-time using a passive stereo camera. To meet the requirements of low-power consumption, we examined the performance of our stereo vision based detector with regard to the camera resolution. It succeeds in differentiating dangerously approaching stairs from safe situations at low resolutions. In the future, our detector will be ported on an embedded platform equipped with a pair of low-resolution and high dynamic range stereo camera for both indoor and outdoor usage with a battery-life of several days.


Note: BOLOGNA, Guido est un chercheur à la HES-SO, HEPIA, depuis 2011.


Keywords:
Conference Type:
full paper
Faculty:
Ingénierie et Architecture
School:
HEPIA - Genève
Institute:
inIT - Institut d'Ingénierie Informatique et des Télécommunications
Publisher:
Zurich, Switzerland, 6-12 September 2014
Date:
2014-09
Zurich, Switzerland
6-12 September 2014
Pagination:
pp. 658-672
Published in:
Lecture Notes in Computer Science; Proceedings of European Conference on Computer Vision: ECCV 2014: Computer Vision - ECCV 2014 Workshops, 6-12 September 2014, Zurich, Switzerland
Series Statement:
LNCS, vol. 8927
DOI:
ISSN:
0302-9743
ISBN:
978-3-319-16198-3
Appears in Collection:

Note: The status of this file is: restricted


 Record created 2020-07-10, last modified 2020-07-17

Fulltext:
Download fulltext
PDF

Rate this document:

Rate this document:
1
2
3
 
(Not yet reviewed)