A Multisize Superpixel Approach for Salient Object Detection Based on Multivariate Normal Distribution Estimation
A Multisize Superpixel Approach for Salient Object Detection Based on Multivariate Normal Distribution Estimation
复制标题
DOI：
10.1109/tip.2014.2361024
复制
发表时间：
2014-10
影响因子：
10.6
通讯作者：
Lei Zhu;Dominik A. Klein;S. Frintrop;ZHIGUO CAO;A. Cremers
中科院分区：
文献类型：
--
作者：
Lei Zhu;Dominik A. Klein;S. Frintrop;ZHIGUO CAO;A. Cremers
提出了一种基于多尺度超像素复杂外观比较的显著目标检测新方法。这些超像素由CIE-Lab颜色空间中的多元正态分布建模，这些分布是从它们所包含的像素中估计的。这种拟合有助于有效地应用欧几里德范数（W2）上的Wasserstein距离来测量元素之间的感知相似性。显著性以两种方式计算。一方面，我们通过概率性地将视觉上相似的超像素分组到集群中并对其紧凑性进行评级来计算全局显着性。另一方面，我们使用相同的距离度量来确定超像素之间的局部中心-环绕对比度。然后，一个创新的局部约束随机游走技术，考虑局部元素之间的相似性平衡内可能的对象和背景的显着性评级。我们的实验结果表明，我们的方法对11个最近发表的国家的最先进的显着性检测方法在五个广泛使用的基准数据集的鲁棒性和效率。
This paper presents a new method for salient object detection based on a sophisticated appearance comparison of multisize superpixels. Those superpixels are modeled by multivariate normal distributions in CIE-Lab color space, which are estimated from the pixels they comprise. This fitting facilitates an efficient application of the Wasserstein distance on the Euclidean norm (W2) to measure perceptual similarity between elements. Saliency is computed in two ways. On the one hand, we compute global saliency by probabilistically grouping visually similar superpixels into clusters and rate their compactness. On the other hand, we use the same distance measure to determine local center-surround contrasts between superpixels. Then, an innovative locally constrained random walk technique that considers local similarity between elements balances the saliency ratings inside probable objects and background. The results of our experiments show the robustness and efficiency of our approach against 11 recently published state-of-the-art saliency detection methods on five widely used benchmark data sets.