Bayesian Saliency via Low and Mid Level Cues

Visual saliency detection is a challenging problem in computer vision, but one of great importance and numerous applications. In this paper, we propose a novel model for bottom-up saliency within the Bayesian framework by exploiting low and mid level cues. In contrast to most existing methods that o...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on image processing Vol. 22; no. 5; pp. 1689 - 1698
Main Authors: Xie, Yulin, Lu, Huchuan, Yang, Ming-Hsuan
Format: Journal Article
Language:English
Published: New York, NY IEEE 01.05.2013
Institute of Electrical and Electronics Engineers
Subjects:
Applied sciences
Artificial intelligence
Bayesian methods
Clustering algorithms
Computational modeling
Computer science; control theory; systems
Exact sciences and technology
Image color analysis
Image processing
Information, signal and communications theory
Laplace equations
Laplacian sparse subspace clustering
Pattern recognition. Digital image processing. Computational geometry
saliency map
Signal and communications theory
Signal processing
Signal representation. Spectral analysis
Signal, noise
Sparse matrices
Telecommunications and information theory
visual saliency
Visualization
Bayes estimation
Computer vision
Automatic classification
State of the art
Subspace method
saliency map
Laplacian sparse subspace clustering
Algorithm
Signal classification
Laplacian
Convex hull
Bayes methods
Visual saliency
ISSN:1057-7149, 1941-0042, 1941-0042
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Visual saliency detection is a challenging problem in computer vision, but one of great importance and numerous applications. In this paper, we propose a novel model for bottom-up saliency within the Bayesian framework by exploiting low and mid level cues. In contrast to most existing methods that operate directly on low level cues, we propose an algorithm in which a coarse saliency region is first obtained via a convex hull of interest points. We also analyze the saliency information with mid level visual cues via superpixels. We present a Laplacian sparse subspace clustering method to group superpixels with local features, and analyze the results with respect to the coarse saliency region to compute the prior saliency map. We use the low level visual cues based on the convex hull to compute the observation likelihood, thereby facilitating inference of Bayesian saliency at each pixel. Extensive experiments on a large data set show that our Bayesian saliency model performs favorably against the state-of-the-art algorithms.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ISSN:1057-7149
1941-0042
1941-0042
DOI:10.1109/TIP.2012.2216276