Road networks as collections of minimum cost paths
详细信息 查看全文
- 作者：Jan Dirk Wegner ; Javier Alexander Montoya-Zegarra ; Konrad Schindler
- 关键词：Aerial ; Multispectral ; Urban ; Networks ; Extraction ; High resolution
- 刊名：ISPRS Journal of Photogrammetry and Remote Sensing
- 出版年：2015
- 出版时间：October 2015
- 年：2015
- 卷：108
- 期：Complete
- 页码：128-137
- 全文大小：4884 K
文摘
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 35a24ab16b8" title="Click to view the MathML source">PN-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.