Saliency Density Maximization for Efficient Visual Objects Discovery
Authors:
- 25 April 2011
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 21 (12) , 1822-1834
Abstract
Detection of salient objects in an image remains a challenging problem despite extensive studies in visual saliency, as the generated saliency map is usually noisy and incomplete. In this paper, we propose a new method to discover the salient object without prior knowledge on its shape and size. By searching the sub-image, i.e., a bounding box of maximum saliency density, the new formulation can automatically crop the salient objects of various sizes in spite of the cluttered background, and is capable to handle different types of saliency maps. A global optimal solution is obtained by the proposed density-based branch-and-bound search. The proposed method can apply to both images and videos. Experimental results on a public dataset of 5000 images show that our unsupervised detection approach is comparable to the state-of-the-art learning-based methods. Promising results are also observed in the salient object detection for videos with a good potential in video retargeting.Keywords
This publication has 35 references indexed in Scilit:
- Object of Interest Detection by Saliency Learning2010
- Discriminative Spatial Attention for Robust Tracking2010
- Static and space-time visual saliency detection by self-resemblanceJournal of Vision, 2009
- SUN: A Bayesian framework for saliency using natural statisticsJournal of Vision, 2008
- Modeling attention to salient proto-objectsNeural Networks, 2006
- Selective visual attention enables learning and recognition of multiple objects in cluttered scenesComputer Vision and Image Understanding, 2005
- Visual attention for region of interest coding in JPEG 2000Journal of Visual Communication and Image Representation, 2003
- A model of saliency-based visual attention for rapid scene analysisIEEE Transactions on Pattern Analysis and Machine Intelligence, 1998
- Episodic theory of the dynamics of spatial attention.Psychological Review, 1995
- Branch-and-Bound Methods: A SurveyOperations Research, 1966