Bayesian Saliency via Low and Mid Level Cues
Bayesian Saliency via Low and Mid Level Cues
复制标题
DOI：
10.1109/tip.2012.2216276
复制
发表时间：
2013-05
影响因子：
10.6
通讯作者：
中科院分区：
文献类型：
--
作者：
视觉显著性检测是计算机视觉中的一个具有挑战性的问题，但也是一个非常重要和广泛应用的问题。在本文中，我们通过利用低水平和中等水平的线索，在贝叶斯框架内提出了一个新的自下而上的显著性模型。与大多数直接在低级线索上操作的现有方法相反，我们提出了一种算法，该算法首先通过兴趣点的凸包获得粗糙显著区域。我们还通过超像素分析了中级视觉线索的显著性信息。提出了一种拉普拉斯稀疏子空间聚类方法，对具有局部特征的超像素进行分组，并对粗显著区域的结果进行分析，从而计算出先验显著图。我们使用基于凸包的低层次视觉线索来计算观测的似然性，从而促进贝叶斯显着性在每个像素上的推断。在大型数据集上进行的大量实验表明，我们的贝叶斯显著性模型与最先进的算法相比表现良好。
Visual saliency detection is a challenging problem in computer vision, but one of great importance and numerous applications. In this paper, we propose a novel model for bottom-up saliency within the Bayesian framework by exploiting low and mid level cues. In contrast to most existing methods that operate directly on low level cues, we propose an algorithm in which a coarse saliency region is first obtained via a convex hull of interest points. We also analyze the saliency information with mid level visual cues via superpixels. We present a Laplacian sparse subspace clustering method to group superpixels with local features, and analyze the results with respect to the coarse saliency region to compute the prior saliency map. We use the low level visual cues based on the convex hull to compute the observation likelihood, thereby facilitating inference of Bayesian saliency at each pixel. Extensive experiments on a large data set show that our Bayesian saliency model performs favorably against the state-of-the-art algorithms.