TY - JOUR

T1 - Salient object detection employing a local tree-structured low-rank representation and foreground consistency

AU - Zhang, Q.

AU - Huo, Z.

AU - Liu, Y.

AU - Pan, Y.

AU - Shan, C.

AU - Han, J.

PY - 2019/8/1

Y1 - 2019/8/1

N2 - 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.

AB - 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.

KW - Background dictionary

KW - Foreground consistency

KW - Salient object detection

KW - Structured low-rank representation

KW - Forestry

KW - Object recognition

KW - Benchmark datasets

KW - Coefficients matrixes

KW - Low-rank matrix recoveries

KW - Low-rank representations

KW - Rank constraints

KW - State-of-the-art methods

KW - Object detection

U2 - 10.1016/j.patcog.2019.03.023

DO - 10.1016/j.patcog.2019.03.023

M3 - Journal article

VL - 92

SP - 119

EP - 134

JO - Pattern Recognition

JF - Pattern Recognition

SN - 0031-3203

ER -