Learning to Predict Video Saliency using Temporal Superpixels

Anurag Singh, Chee-Hung Henry Chu, Michael A. Pratt

2015

Abstract

Visual Saliency of a video sequence can be computed by combining spatial and temporal features that attract a user’s attention to a group of pixels. We present a method that computes video saliency by integrating these features: color dissimilarity, objectness measure, motion difference, and boundary score. We use temporal clusters of pixels, or temporal superpixels, to simulate attention associated with a group of moving pixels in a video sequence. The features are combined using weights learned by a linear support vector machine in an online fashion. The temporal linkage for superpixels is then used to find the saliency flow across the image frames. We experimentally demonstrate the efficacy of the proposed method and that the method has better performance when compared to state-of-the-art methods.

Paper Citation

in Harvard Style

Singh A., Henry Chu C. and A. Pratt M. (2015). Learning to Predict Video Saliency using Temporal Superpixels . In Proceedings of the International Conference on Pattern Recognition Applications and Methods - Volume 2: ICPRAM, ISBN 978-989-758-077-2, pages 201-209. DOI: 10.5220/0005206402010209

in Bibtex Style

@conference{icpram15,
author={Anurag Singh and Chee-Hung Henry Chu and Michael A. Pratt},
title={Learning to Predict Video Saliency using Temporal Superpixels},
booktitle={Proceedings of the International Conference on Pattern Recognition Applications and Methods - Volume 2: ICPRAM,},
year={2015},
pages={201-209},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0005206402010209},
isbn={978-989-758-077-2},
}

in EndNote Style

TY - CONF
JO - Proceedings of the International Conference on Pattern Recognition Applications and Methods - Volume 2: ICPRAM,
TI - Learning to Predict Video Saliency using Temporal Superpixels
SN - 978-989-758-077-2
AU - Singh A.
AU - Henry Chu C.
AU - A. Pratt M.
PY - 2015
SP - 201
EP - 209
DO - 10.5220/0005206402010209