Saliency Detection via Dense and Sparse Reconstruction

In this paper, we propose a visual saliency detection algorithm from the perspective of reconstruction errors. The image boundaries are first extracted via super pixels as likely cues for background templates, from which dense and sparse appearance models are constructed. For each image region, we f...

Full description

Saved in:
Bibliographic Details
Main Authors: Li, Xiaohui, Lu, Huchuan, Zhang, Lihe, Ruan, Xiang, Yang, Ming-Hsuan
Format: Conference Proceeding
Language:English
Subjects:
Algorithms
Background noise
Bayes methods
Boundaries
Computational modeling
Computer vision
Error detection
Errors
Image reconstruction
Image segmentation
Mathematical models
Measurement uncertainty
Recall
Reconstruction
Visualization
Citations: Items that cite this one
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In this paper, we propose a visual saliency detection algorithm from the perspective of reconstruction errors. The image boundaries are first extracted via super pixels as likely cues for background templates, from which dense and sparse appearance models are constructed. For each image region, we first compute dense and sparse reconstruction errors. Second, the reconstruction errors are propagated based on the contexts obtained from K-means clustering. Third, pixel-level saliency is computed by an integration of multi-scale reconstruction errors and refined by an object-biased Gaussian model. We apply the Bayes formula to integrate saliency measures based on dense and sparse reconstruction errors. Experimental results show that the proposed algorithm performs favorably against seventeen state-of-the-art methods in terms of precision and recall. In addition, the proposed algorithm is demonstrated to be more effective in highlighting salient objects uniformly and robust to background noise.
ISSN:1550-5499
2380-7504
DOI:10.1109/ICCV.2013.370