Fusion of multiple visual cues for visual saliency extraction from wearable camera settings with strong motion

Authors:
Hugo Boujut;Jenny Benois-Pineau;Remi Megret
Affiliations:
LaBRI, UMR 5800, University of Bordeaux, Talence, France;LaBRI, UMR 5800, University of Bordeaux, Talence, France;IMS, UMR 5218, University of Bordeaux, Talence, France
Venue:
ECCV'12 Proceedings of the 12th international conference on Computer Vision - Volume Part III
Year:
2012

Citing 8
Cited 1

Visual Contextual Awareness in Wearable Computing

ISWC '98 Proceedings of the 2nd IEEE International Symposium on Wearable Computers
Modelling Spatio-Temporal Saliency to Predict Gaze Direction for Short Videos

International Journal of Computer Vision
Human Daily Activities Indexing in Videos from Wearable Cameras for Monitoring of Patients with Dementia Diseases

ICPR '10 Proceedings of the 2010 20th International Conference on Pattern Recognition
A color-action perceptual approach to the classification of animated movies

Proceedings of the 1st ACM International Conference on Multimedia Retrieval
Detection of moving foreground objects in videos with strong camera motion

Pattern Analysis & Applications
A metric for no-reference video quality assessment for HD TV delivery based on saliency maps

ICME '11 Proceedings of the 2011 IEEE International Conference on Multimedia and Expo
Fast and Robust Generation of Feature Maps for Region-Based Visual Attention

IEEE Transactions on Image Processing
Discovering important people and objects for egocentric video summarization

CVPR '12 Proceedings of the 2012 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

Modeling instrumental activities of daily living in egocentric vision as sequences of active objects and context for alzheimer disease research

Proceedings of the 1st ACM international workshop on Multimedia indexing and information retrieval for healthcare

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper we are interested in the saliency of visual content from wearable cameras. The subjective saliency in wearable video is studied first due to the psycho-visual experience on this content. Then the method for objective saliency map computation with a specific contribution based on geometrical saliency is proposed. Fusion of spatial, temporal and geometric cues in an objective saliency map is realized by the multiplicative operator. Resulting objective saliency maps are evaluated against the subjective maps with promising results, highlighting interesting performance of proposed geometric saliency model.