Details
| Original language | English |
|---|---|
| Pages (from-to) | 8-28 |
| Number of pages | 21 |
| Journal | Photogrammetric Record |
| Volume | 27 |
| Issue number | 137 |
| Publication status | Published - 14 Mar 2012 |
Abstract
In this paper, an algorithm for the extraction of road networks in suburban areas is presented. The algorithm is region-based and uses high-resolution colour infrared images as well as, optionally, a digital surface model (DSM). The road extraction starts with a segmentation using the normalised cuts algorithm; afterwards the segments are grouped. Road sections are extracted from the grouped segments. Road sections that are likely to belong to the same road are connected to subgraphs in the next step. To eliminate false connections in the subgraphs, context objects such as vehicles, buildings and trees are employed. The remaining road strings, represented by their centre lines, are connected to a road network. The process employs combinations of radiometric and geometric features, derived from knowledge about the appearance of roads in suburban areas. Results are presented for two test data-sets, acquired by different sensors. A quantitative analysis is performed for the quality of the road extraction as well as the topological quality of the extracted network.
Keywords
- Completeness and correctness, Context, Network generation, Normalised cuts, Road extraction, Suburban areas
ASJC Scopus subject areas
- Engineering(all)
- Engineering (miscellaneous)
- Computer Science(all)
- Computer Science Applications
- Earth and Planetary Sciences(all)
- Computers in Earth Sciences
- Earth and Planetary Sciences(all)
- Earth and Planetary Sciences (miscellaneous)
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
In: Photogrammetric Record, Vol. 27, No. 137, 14.03.2012, p. 8-28.
Research output: Contribution to journal › Article › Research › peer review
}
TY - JOUR
T1 - Road Network Extraction in Suburban Areas
AU - Grote, Anne
AU - Heipke, Christian
AU - Rottensteiner, Franz
PY - 2012/3/14
Y1 - 2012/3/14
N2 - In this paper, an algorithm for the extraction of road networks in suburban areas is presented. The algorithm is region-based and uses high-resolution colour infrared images as well as, optionally, a digital surface model (DSM). The road extraction starts with a segmentation using the normalised cuts algorithm; afterwards the segments are grouped. Road sections are extracted from the grouped segments. Road sections that are likely to belong to the same road are connected to subgraphs in the next step. To eliminate false connections in the subgraphs, context objects such as vehicles, buildings and trees are employed. The remaining road strings, represented by their centre lines, are connected to a road network. The process employs combinations of radiometric and geometric features, derived from knowledge about the appearance of roads in suburban areas. Results are presented for two test data-sets, acquired by different sensors. A quantitative analysis is performed for the quality of the road extraction as well as the topological quality of the extracted network.
AB - In this paper, an algorithm for the extraction of road networks in suburban areas is presented. The algorithm is region-based and uses high-resolution colour infrared images as well as, optionally, a digital surface model (DSM). The road extraction starts with a segmentation using the normalised cuts algorithm; afterwards the segments are grouped. Road sections are extracted from the grouped segments. Road sections that are likely to belong to the same road are connected to subgraphs in the next step. To eliminate false connections in the subgraphs, context objects such as vehicles, buildings and trees are employed. The remaining road strings, represented by their centre lines, are connected to a road network. The process employs combinations of radiometric and geometric features, derived from knowledge about the appearance of roads in suburban areas. Results are presented for two test data-sets, acquired by different sensors. A quantitative analysis is performed for the quality of the road extraction as well as the topological quality of the extracted network.
KW - Completeness and correctness
KW - Context
KW - Network generation
KW - Normalised cuts
KW - Road extraction
KW - Suburban areas
UR - http://www.scopus.com/inward/record.url?scp=84858321123&partnerID=8YFLogxK
U2 - 10.1111/j.1477-9730.2011.00670.x
DO - 10.1111/j.1477-9730.2011.00670.x
M3 - Article
AN - SCOPUS:84858321123
VL - 27
SP - 8
EP - 28
JO - Photogrammetric Record
JF - Photogrammetric Record
SN - 0031-868X
IS - 137
ER -