Salient object detection employing a local tree-structured low-rank representation and foreground consistency

Zhang, Q. and Huo, Z. and Liu, Y. and Pan, Y. and Shan, C. and Han, J. (2019) Salient object detection employing a local tree-structured low-rank representation and foreground consistency. Pattern Recognition, 92. pp. 119-134. ISSN 0031-3203

Full text not available from this repository.

Abstract

We propose a local tree-structured low-rank representation (TS-LRR) model to detect salient objects under the complicated background with diverse local regions, which is problematic for most low-rank matrix recovery (LRMR) based salient object detection methods. We first impose a local tree-structured low-rank constraint on the representation coefficients matrix to capture the complicated background. Specifically, a primitive background dictionary is constructed for TS-LRR to promote its background representation ability, and thus enlarge the gap between the salient objects and the background. We then impose a group-sparsity constraint on the sparse error matrix with the intention to ensure the saliency consistency among patches with similar features. At last, a foreground consistency is introduced to identically highlight the distinctive regions within the salient object. Experimental results on three public benchmark datasets demonstrate the effectiveness and superiority of the proposed model over the state-of-the-art methods.

Item Type:
Journal Article
Journal or Publication Title:
Pattern Recognition
Uncontrolled Keywords:
/dk/atira/pure/subjectarea/asjc/1700/1702
Subjects:
?? background dictionaryforeground consistencysalient object detectionstructured low-rank representationforestryobject recognitionbenchmark datasetscoefficients matrixeslow-rank matrix recoverieslow-rank representationsrank constraintsstate-of-the-art method ??
ID Code:
132752
Deposited By:
Deposited On:
11 Jul 2019 13:05
Refereed?:
Yes
Published?:
Published
Last Modified:
15 Jul 2024 19:15