Manifold SLIC: A Fast Method to Compute Content-Sensitive Superpixels

Manifold SLIC: A Fast Method to Compute Content-Sensitive Superpixels
复制标题

Manifold SLIC:计算内容敏感超像素的快速方法

DOI:
10.1109/cvpr.2016.77
复制
发表时间:
2016-06
期刊:
2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
影响因子:
--
通讯作者:
Ying He
Ying He
中科院分区:
其他
文献类型:
--
作者:
Yong Jin Liu;Cheng Chi Yu;Min Jing Yu;Ying He

文献摘要

参考文献

被引文献

相似文献

超像素是感知上有意义的原子区域,可以有效地捕获图像特征。在计算均匀超像素的各种方法中,简单线性迭代聚类(SLIC)由于其简单性和高性能而受到欢迎。在本文中,我们扩展了SLIC来计算内容敏感的超像素,即,内容密集区域中的小超像素(例如,具有高强度或颜色变化)和内容稀疏区域中的大超像素。我们将图像I映射到一个二维流形M 5上,而不是传统的将像素聚类在I中的SLIC方法,其面积元素是I中内容密度的一个很好的度量。本文提出了一种有效的方法来计算M上的约束质心Voronoi曲面细分(RCVT),它是一种均匀的曲面细分,可以在I上产生内容敏感的超像素。与其他通过测地距离表征内容敏感性的算法不同,流形SLIC通过测量M上的Voronoi单元的面积来解决这个问题,这可以以非常低的成本计算。因此,它比最先进的内容敏感超像素算法快10倍。我们评估流形SLIC和七个代表性的方法在BSDS 500基准,并观察到我们的方法优于现有的方法。
Superpixels are perceptually meaningful atomic regions that can effectively capture image features. Among various methods for computing uniform superpixels, simple linear iterative clustering (SLIC) is popular due to its simplicity and high performance. In this paper, we extend SLIC to compute content-sensitive superpixels, i.e., small superpixels in content-dense regions (e.g., with high intensity or color variation) and large superpixels in content-sparse regions. Rather than the conventional SLIC method that clusters pixels in ℝ5, we map the image I to a 2-dimensional manifold M ⊂ ℝ5, whose area elements are a good measure of the content density in I. We propose an efficient method to compute restricted centroidal Voronoi tessellation (RCVT) - a uniform tessellation - on M, which induces the content-sensitive superpixels in I. Unlike other algorithms that characterize content-sensitivity by geodesic distances, manifold SLIC tackles the problem by measuring areas of Voronoi cells on M, which can be computed at a very low cost. As a result, it runs 10 times faster than the state-of-the-art content-sensitive superpixels algorithm. We evaluate manifold SLIC and seven representative methods on the BSDS500 benchmark and observe that our method outperforms the existing methods.
用于从单目图像中提取 2.1D 草图的全局能量优化框架
DOI: 10.1016/j.gmod.2014.03.015
发表时间: 2014-09
期刊: Graphical Models
影响因子: 1.7
作者:
Kai-Yun Li;Kai-Yun Li;Xiaolan Fu;Xiaolan Fu
通讯作者: Xiaolan Fu
DOI: 10.1109/34.868688
发表时间: 2000-08-01
影响因子: 23.6
作者:
Shi, JB;Malik, J
通讯作者: Malik, J
DOI: 10.1109/tpami.2010.221
发表时间: 2011-08
影响因子: 23.6
作者:
Yong-Jin Liu;Zhanqing Chen;K. Tang
通讯作者: Yong-Jin Liu;Zhanqing Chen;K. Tang
二流形离散 Voronoi 近似中骨架的半连续性
DOI: 10.1109/tpami.2015.2430342
发表时间: 2015-09
影响因子: 23.6
作者:
Liu Yong Jin
通讯作者: Liu Yong Jin
DOI: 10.1023/b:visi.0000022288.19776.77
发表时间: 2004-09-01
影响因子: 19.5
作者:
Felzenszwalb, PF;Huttenlocher, DP
通讯作者: Huttenlocher, DP