Saliency detection via dense and sparse reconstruction

Xiaohui Li, Huchuan Lu, Lihe Zhang, Xiang Ruan, Ming Hsuan Yang

Research output: Chapter in Book/Report/Conference proceedingConference contribution

470 Citations (Scopus)

Abstract

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.

Original languageEnglish
Title of host publicationProceedings - 2013 IEEE International Conference on Computer Vision, ICCV 2013
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages2976-2983
Number of pages8
ISBN (Print)9781479928392
DOIs
Publication statusPublished - 2013 Jan 1
Event2013 14th IEEE International Conference on Computer Vision, ICCV 2013 - Sydney, NSW, Australia
Duration: 2013 Dec 12013 Dec 8

Publication series

NameProceedings of the IEEE International Conference on Computer Vision
ISSN (Print)1550-5499

Other

Other2013 14th IEEE International Conference on Computer Vision, ICCV 2013
CountryAustralia
CitySydney, NSW
Period13/12/113/12/8

Fingerprint

Pixels

All Science Journal Classification (ASJC) codes

  • Software
  • Computer Vision and Pattern Recognition

Cite this

Li, X., Lu, H., Zhang, L., Ruan, X., & Yang, M. H. (2013). Saliency detection via dense and sparse reconstruction. In Proceedings - 2013 IEEE International Conference on Computer Vision, ICCV 2013 (pp. 2976-2983). [6751481] (Proceedings of the IEEE International Conference on Computer Vision). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICCV.2013.370
Li, Xiaohui ; Lu, Huchuan ; Zhang, Lihe ; Ruan, Xiang ; Yang, Ming Hsuan. / Saliency detection via dense and sparse reconstruction. Proceedings - 2013 IEEE International Conference on Computer Vision, ICCV 2013. Institute of Electrical and Electronics Engineers Inc., 2013. pp. 2976-2983 (Proceedings of the IEEE International Conference on Computer Vision).
@inproceedings{bad591a01bd542e199829dbd03ab2ab5,
title = "Saliency detection via dense and sparse reconstruction",
abstract = "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.",
author = "Xiaohui Li and Huchuan Lu and Lihe Zhang and Xiang Ruan and Yang, {Ming Hsuan}",
year = "2013",
month = "1",
day = "1",
doi = "10.1109/ICCV.2013.370",
language = "English",
isbn = "9781479928392",
series = "Proceedings of the IEEE International Conference on Computer Vision",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "2976--2983",
booktitle = "Proceedings - 2013 IEEE International Conference on Computer Vision, ICCV 2013",
address = "United States",

}

Li, X, Lu, H, Zhang, L, Ruan, X & Yang, MH 2013, Saliency detection via dense and sparse reconstruction. in Proceedings - 2013 IEEE International Conference on Computer Vision, ICCV 2013., 6751481, Proceedings of the IEEE International Conference on Computer Vision, Institute of Electrical and Electronics Engineers Inc., pp. 2976-2983, 2013 14th IEEE International Conference on Computer Vision, ICCV 2013, Sydney, NSW, Australia, 13/12/1. https://doi.org/10.1109/ICCV.2013.370

Saliency detection via dense and sparse reconstruction. / Li, Xiaohui; Lu, Huchuan; Zhang, Lihe; Ruan, Xiang; Yang, Ming Hsuan.

Proceedings - 2013 IEEE International Conference on Computer Vision, ICCV 2013. Institute of Electrical and Electronics Engineers Inc., 2013. p. 2976-2983 6751481 (Proceedings of the IEEE International Conference on Computer Vision).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Saliency detection via dense and sparse reconstruction

AU - Li, Xiaohui

AU - Lu, Huchuan

AU - Zhang, Lihe

AU - Ruan, Xiang

AU - Yang, Ming Hsuan

PY - 2013/1/1

Y1 - 2013/1/1

N2 - 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.

AB - 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.

UR - http://www.scopus.com/inward/record.url?scp=84898822478&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84898822478&partnerID=8YFLogxK

U2 - 10.1109/ICCV.2013.370

DO - 10.1109/ICCV.2013.370

M3 - Conference contribution

AN - SCOPUS:84898822478

SN - 9781479928392

T3 - Proceedings of the IEEE International Conference on Computer Vision

SP - 2976

EP - 2983

BT - Proceedings - 2013 IEEE International Conference on Computer Vision, ICCV 2013

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

Li X, Lu H, Zhang L, Ruan X, Yang MH. Saliency detection via dense and sparse reconstruction. In Proceedings - 2013 IEEE International Conference on Computer Vision, ICCV 2013. Institute of Electrical and Electronics Engineers Inc. 2013. p. 2976-2983. 6751481. (Proceedings of the IEEE International Conference on Computer Vision). https://doi.org/10.1109/ICCV.2013.370