Graph-Regularized Saliency Detection With Convex-Hull-Based Center Prior
Graph-Regularized Saliency Detection With Convex-Hull-Based Center Prior
复制标题
DOI：
10.1109/lsp.2013.2260737
复制
发表时间：
2013-04
影响因子：
3.9
通讯作者：
Chuan Yang;L. Zhang;Huchuan Lu
中科院分区：
文献类型：
--
作者：
Chuan Yang;L. Zhang;Huchuan Lu
对象级显着性检测对于许多基于内容的计算机视觉任务非常有用。在这封信中，我们通过利用对比度、中心和平滑度先验，提出了一种新颖的自下而上的显着目标检测方法。首先，我们使用对比度和中心先验计算初始显着性图。与大多数现有的基于中心先验的方法不同，我们应用兴趣点的凸包来估计显着对象的中心，而不是直接使用图像中心。这种策略使得显着性结果对于对象的位置更加稳健。其次，我们通过图正则化最小化连续的成对显着性能量函数来细化初始显着性图，这鼓励相邻像素或片段采用相似的显着性值（即先验平滑度）。平滑先验使得所提出的方法能够均匀突出显着对象，同时有效地抑制背景。对大型数据集的大量实验表明，所提出的方法在准确性和效率方面优于最先进的方法。
Object level saliency detection is useful for many content-based computer vision tasks. In this letter, we present a novel bottom-up salient object detection approach by exploiting contrast, center and smoothness priors. First, we compute an initial saliency map using contrast and center priors. Unlike most existing center prior based methods, we apply the convex hull of interest points to estimate the center of the salient object rather than directly use the image center. This strategy makes the saliency result more robust to the location of objects. Second, we refine the initial saliency map through minimizing a continuous pairwise saliency energy function with graph regularization which encourages adjacent pixels or segments to take the similar saliency value (i.e., smoothness prior). The smoothness prior enables the proposed method to uniformly highlight the salient object and simultaneously suppress the background effectively. Extensive experiments on a large dataset demonstrate that the proposed method performs favorably against the state-of-the-art methods in terms of accuracy and efficiency.