Dense and Sparse Reconstruction Error Based Saliency Descriptor
Dense and Sparse Reconstruction Error Based Saliency Descriptor
复制标题
基于显着性描述符的密集和稀疏重建错误
DOI：
10.1109/tip.2016.2524198
复制
发表时间：
2016-04-01
影响因子：
10.6
通讯作者：
Yang, Ming-Hsuan
中科院分区：
文献类型：
--
作者：
Lu, Huchuan;Li, Xiaohui;Yang, Ming-Hsuan
本文从重建误差的角度提出了一种视觉显著检测算法。首先通过超像素提取图像边界作为背景模板的可能线索，从背景模板中构建密集和稀疏外观模型。首先，我们计算每个图像区域的背景模板的密集和稀疏重建误差。其次，基于K-均值聚类得到的上下文传播重建误差。第三，对多尺度重建误差进行积分，计算像素级重建误差。然后对像素级的密集和稀疏重建误差进行图像紧凑度加权，可以更准确地检测出显著程度。此外，我们还提出了一种新的结合显著图的贝叶斯积分方法，并将其应用于基于密集和稀疏重建误差的两种显著度量的整合。在三个公共标准显著目标检测数据库上的实验结果表明，该算法在查准率、召回率和F-度量等方面均优于24种最新方法。
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 pixellevel 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.