Dense and Sparse Reconstruction Error Based Saliency Descriptor

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

Research output: Contribution to journalArticle

59 Citations (Scopus)

Abstract

In this paper, we propose a visual saliency detection algorithm from the perspective of reconstruction error. The image boundaries are first extracted via superpixels as likely cues for background templates, from which dense and sparse appearance models are constructed. First, we compute dense and sparse reconstruction errors on the background templates for each image region. Second, the reconstruction errors are propagated based on the contexts obtained from K -means clustering. Third, the pixel-level reconstruction error is computed by the integration of multi-scale reconstruction errors. Both the pixel-level dense and sparse reconstruction errors are then weighted by image compactness, which could more accurately detect saliency. In addition, we introduce a novel Bayesian integration method to combine saliency maps, which is applied to integrate the two saliency measures based on dense and sparse reconstruction errors. Experimental results show that the proposed algorithm performs favorably against 24 state-of-the-art methods in terms of precision, recall, and F-measure on three public standard salient object detection databases.

Original languageEnglish
Article number7396959
Pages (from-to)1592-1603
Number of pages12
JournalIEEE Transactions on Image Processing
Volume25
Issue number4
DOIs
Publication statusPublished - 2016 Apr

Fingerprint

Pixels
Object detection

All Science Journal Classification (ASJC) codes

  • Software
  • Computer Graphics and Computer-Aided Design

Cite this

Lu, Huchuan ; Li, Xiaohui ; Zhang, Lihe ; Ruan, Xiang ; Yang, Ming Hsuan. / Dense and Sparse Reconstruction Error Based Saliency Descriptor. In: IEEE Transactions on Image Processing. 2016 ; Vol. 25, No. 4. pp. 1592-1603.
@article{403bd820ceb64d648561214c4926d343,
title = "Dense and Sparse Reconstruction Error Based Saliency Descriptor",
abstract = "In this paper, we propose a visual saliency detection algorithm from the perspective of reconstruction error. The image boundaries are first extracted via superpixels as likely cues for background templates, from which dense and sparse appearance models are constructed. First, we compute dense and sparse reconstruction errors on the background templates for each image region. Second, the reconstruction errors are propagated based on the contexts obtained from K -means clustering. Third, the pixel-level reconstruction error is computed by the integration of multi-scale reconstruction errors. Both the pixel-level dense and sparse reconstruction errors are then weighted by image compactness, which could more accurately detect saliency. In addition, we introduce a novel Bayesian integration method to combine saliency maps, which is applied to integrate the two saliency measures based on dense and sparse reconstruction errors. Experimental results show that the proposed algorithm performs favorably against 24 state-of-the-art methods in terms of precision, recall, and F-measure on three public standard salient object detection databases.",
author = "Huchuan Lu and Xiaohui Li and Lihe Zhang and Xiang Ruan and Yang, {Ming Hsuan}",
year = "2016",
month = "4",
doi = "10.1109/TIP.2016.2524198",
language = "English",
volume = "25",
pages = "1592--1603",
journal = "IEEE Transactions on Image Processing",
issn = "1057-7149",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "4",

}

Dense and Sparse Reconstruction Error Based Saliency Descriptor. / Lu, Huchuan; Li, Xiaohui; Zhang, Lihe; Ruan, Xiang; Yang, Ming Hsuan.

In: IEEE Transactions on Image Processing, Vol. 25, No. 4, 7396959, 04.2016, p. 1592-1603.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Dense and Sparse Reconstruction Error Based Saliency Descriptor

AU - Lu, Huchuan

AU - Li, Xiaohui

AU - Zhang, Lihe

AU - Ruan, Xiang

AU - Yang, Ming Hsuan

PY - 2016/4

Y1 - 2016/4

N2 - In this paper, we propose a visual saliency detection algorithm from the perspective of reconstruction error. The image boundaries are first extracted via superpixels as likely cues for background templates, from which dense and sparse appearance models are constructed. First, we compute dense and sparse reconstruction errors on the background templates for each image region. Second, the reconstruction errors are propagated based on the contexts obtained from K -means clustering. Third, the pixel-level reconstruction error is computed by the integration of multi-scale reconstruction errors. Both the pixel-level dense and sparse reconstruction errors are then weighted by image compactness, which could more accurately detect saliency. In addition, we introduce a novel Bayesian integration method to combine saliency maps, which is applied to integrate the two saliency measures based on dense and sparse reconstruction errors. Experimental results show that the proposed algorithm performs favorably against 24 state-of-the-art methods in terms of precision, recall, and F-measure on three public standard salient object detection databases.

AB - In this paper, we propose a visual saliency detection algorithm from the perspective of reconstruction error. The image boundaries are first extracted via superpixels as likely cues for background templates, from which dense and sparse appearance models are constructed. First, we compute dense and sparse reconstruction errors on the background templates for each image region. Second, the reconstruction errors are propagated based on the contexts obtained from K -means clustering. Third, the pixel-level reconstruction error is computed by the integration of multi-scale reconstruction errors. Both the pixel-level dense and sparse reconstruction errors are then weighted by image compactness, which could more accurately detect saliency. In addition, we introduce a novel Bayesian integration method to combine saliency maps, which is applied to integrate the two saliency measures based on dense and sparse reconstruction errors. Experimental results show that the proposed algorithm performs favorably against 24 state-of-the-art methods in terms of precision, recall, and F-measure on three public standard salient object detection databases.

UR - http://www.scopus.com/inward/record.url?scp=84962575891&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84962575891&partnerID=8YFLogxK

U2 - 10.1109/TIP.2016.2524198

DO - 10.1109/TIP.2016.2524198

M3 - Article

AN - SCOPUS:84962575891

VL - 25

SP - 1592

EP - 1603

JO - IEEE Transactions on Image Processing

JF - IEEE Transactions on Image Processing

SN - 1057-7149

IS - 4

M1 - 7396959

ER -