Road networks as collections of minimum cost paths
| Autor: | Konrad Schindler, Jan Dirk Wegner, Javier A. Montoya-Zegarra |
|---|---|
| Rok vydání: | 2015 |
| Předmět: |
Conditional random field
Pixel Computer science Multispectral image Probabilistic logic Global Map computer.software_genre Atomic and Molecular Physics and Optics Computer Science Applications Cut Graph (abstract data type) Data mining Computers in Earth Sciences Engineering (miscellaneous) Algorithm computer Potts model |
| Zdroj: | ISPRS Journal of Photogrammetry and Remote Sensing. 108:128-137 |
| ISSN: | 0924-2716 |
| DOI: | 10.1016/j.isprsjprs.2015.07.002 |
| Popis: | 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. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full Text from ScienceDirect