Road networks as collections of minimum cost paths
Road networks as collections of minimum cost paths
复制标题
DOI：
10.1016/j.isprsjprs.2015.07.002
复制
发表时间：
2015-10
影响因子：
12.7
通讯作者：
J. D. Wegner;Javier A. Montoya-Zegarra;K. Schindler
中科院分区：
文献类型：
--
作者：
J. D. Wegner;Javier A. Montoya-Zegarra;K. Schindler
我们提出了一个概率表示的网络结构的图像。我们的目标应用是从航空图像中提取城市道路。道路看起来像薄的，细长的，部分弯曲的结构，形成一个循环图，这种复杂的布局需要一个先验，超越标准的平滑度和共生假设。在所提出的模型中，网络被表示为连接远距离（超）像素的1D路径的联合。通过在前景（道路）可能性中搜索最小成本路径，以尽可能多地包含真实网络的方式构建一大组假定的候选路径。选择候选路径的最佳子集被视为高阶条件随机场中的MAP推理。每条路径形成一个具有团势的高阶团，该团势将具有高累积道路证据的团的成员节点吸引到前景标签。该配方诱导一个强大的P N-Potts模型，可以找到一个全球MAP解决方案，有效地与图形切割。两个道路数据集的实验表明，该模型显着提高了每像素的精度，以及相对于几个基线的整体拓扑网络的质量。
We present a probabilistic representation of network structures in images. Our target application is the extraction of urban roads from aerial images. Roads appear as thin, elongated, partially curved structures forming a loopy graph, and this complex layout requires a prior that goes beyond standard smoothness and co-occurrence assumptions. In the proposed model the network is represented as a union of 1D paths connecting distant (super-) pixels. A large set of putative candidate paths is constructed in such a way that they include the true network as much as possible, by searching for minimum cost paths in the foreground (road) likelihood. Selecting the optimal subset of candidate paths is posed as MAP inference in a higher-order conditional random field. Each path forms a higher-order clique with a type of clique potential, which attracts the member nodes of cliques with high cumulative road evidence to the foreground label. That formulation induces a robust P N-Potts model, for which a global MAP solution can be found efficiently with graph cuts. Experiments with two road data sets show that the proposed model significantly improves per-pixel accuracies as well as the overall topological network quality with respect to several baselines.