Segmenting Planar Superpixel Adjacency Graphs w.r.t. Non-planar Superpixel Affinity Graphs
Segmenting Planar Superpixel Adjacency Graphs w.r.t. Non-planar Superpixel Affinity Graphs
复制标题
分割平面超像素邻接图 w.r.t.
DOI：
10.1007/978-3-642-40395-8_20
复制
发表时间：
2013
期刊：
影响因子：
--
通讯作者：
H. Pfister
中科院分区：
文献类型：
--
作者：
Björn Andres;Julian Yarkony;B. S. Manjunath;Steffen Kirchhoff;Engin Türetken;Charless C. Fowlkes;H. Pfister
我们从图划分的角度解决了将图像分割成未知数量的片段的问题。具体来说，我们考虑非相邻超像素之间的所有亲和力都为负的超像素亲和力图的最小多分割。我们提出了一个拉格朗日分解松弛法和一个约束的重参数化集，我们可以精确有效地优化。我们的贡献是展示了如果亲和图是非平面的，如何利用邻接图的平面性。实验证明了该方法在用户辅助图像分割中的有效性，并在实践中证明了松弛问题的求解速度快，松弛程度高。
We address the problem of segmenting an image into a previously unknown number of segments from the perspective of graph partitioning. Specifically, we consider minimum multicuts of superpixel affinity graphs in which all affinities between non-adjacent superpixels are negative. We propose a relaxation by Lagrangian decomposition and a constrained set of re-parameterizations for which we can optimize exactly and efficiently. Our contribution is to show how the planarity of the adjacency graph can be exploited if the affinity graph is non-planar. We demonstrate the effectiveness of this approach in user-assisted image segmentation and show that the solution of the relaxed problem is fast and the relaxation is tight in practice.