• Home
  1. Home
  2. Depth-based detection of salient moving objects in sonified videos for blind users
Proceedings chapter
OA Policy
English

Depth-based detection of salient moving objects in sonified videos for blind users

Contributors

Deville, Benoît; Bologna, Guido; Vinckenbosch, Michel; Pun, Thierry

Presented at

Funchal, Madeira, Portugal, Jan. 22-25

Published in

Proceedings of the Third International Conference on Computer Vision Theory and Applications, VISAPP 2008, p. 434-439

Publication date

2008

Abstract

The context of this work is the development of a mobility aid for visually impaired persons. We present here an original approach for a real time alerting system, based on the detection of visual salient parts in videos. The particularity of our approach lies in the use of a new feature map constructed from the depth gradient. A distance function is described, which takes into account both stereoscopic camera limitations and user's choices. We also report how we automatically estimate the contribution of conspicuity maps, which enables the unsupervised determination of the final saliency map. We demonstrate here that this additional depth-based feature map allows the system to detect salient regions with good accuracy in most situations, even in the presence of noisy disparity maps.

UNIGE affiliation entities

UNIGE research groups

Citation (ISO format)

DEVILLE, Benoît et al. Depth-based detection of salient moving objects in sonified videos for blind users. In: Proceedings of the Third International Conference on Computer Vision Theory and Applications, VISAPP 2008. Funchal, Madeira, Portugal. [s.l.] : [s.n.], 2008. p. 434–439.

Main files (1)

Proceedings chapter (Accepted version)

Identifiers

  • PID : unige:47699

Additional URL for this publication

http://dblp.uni-trier.de/rec/bib/conf/visapp/DevilleBVP08
618views
263downloads

Technical informations

Creation

06/03/2015 17:12:08

First validation

06/03/2015 17:12:08

Update

14/03/2023 22:58:43

Status update

14/03/2023 22:58:42

Last indexation

30/10/2024 23:17:57
All rights reserved by Archive ouverte UNIGE and the University of Geneva
OpenAIRE Indexed & Validated