Final published version
Research output: Contribution to Journal/Magazine › Journal article › peer-review
Research output: Contribution to Journal/Magazine › Journal article › peer-review
}
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 -