Details
| Original language | English |
|---|---|
| Pages (from-to) | 17-24 |
| Number of pages | 8 |
| Journal | International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences - ISPRS Archives |
| Volume | 40 |
| Issue number | 3 |
| Publication status | Published - 11 Aug 2014 |
| Event | ISPRS Technical Commission III Symposium 2014 - Zurich, Switzerland Duration: 5 Sept 2014 → 7 Sept 2014 |
Abstract
This paper proposes a two-layer Conditional Random Field model for simultaneous classification of land cover and land use. Both classification tasks are integrated into a unified graphical model, which is reasonable due to the fact that land cover and land use exhibit strong contextual dependencies. In the CRF, we distinguish a land cover layer and a land use layer. Both layers differ with respect to the entities corresponding to the nodes and the classes to be distinguished. In the land cover layer, the nodes correspond to superpixels extracted from the image data, whereas in the land use layer the nodes correspond to objects of a geospatial land use database. Statistical dependencies between land cover and land use are explicitly modelled as pair-wise potentials. Thus, we obtain a consistent model, where the relations between land cover and land use are learned from representative training data. The approach is designed for input data based on aerial images. Experiments are performed on an urban test site. The experiments show the feasibility of the combination of both classification tasks into one overall approach and investigate the influence of the size of the superpixels on the classification result.
Keywords
- Conditional Random Fields, Contextual classification, Land use classification, Multi-layer
ASJC Scopus subject areas
- Computer Science(all)
- Information Systems
- Social Sciences(all)
- Geography, Planning and Development
Sustainable Development Goals
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
In: International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences - ISPRS Archives, Vol. 40, No. 3, 11.08.2014, p. 17-24.
Research output: Contribution to journal › Conference article › Research › peer review
}
TY - JOUR
T1 - A two-layer Conditional Random Field model for simultaneous classification of land cover and land use
AU - Albert, L.
AU - Rottensteiner, F.
AU - Heipke, C.
PY - 2014/8/11
Y1 - 2014/8/11
N2 - This paper proposes a two-layer Conditional Random Field model for simultaneous classification of land cover and land use. Both classification tasks are integrated into a unified graphical model, which is reasonable due to the fact that land cover and land use exhibit strong contextual dependencies. In the CRF, we distinguish a land cover layer and a land use layer. Both layers differ with respect to the entities corresponding to the nodes and the classes to be distinguished. In the land cover layer, the nodes correspond to superpixels extracted from the image data, whereas in the land use layer the nodes correspond to objects of a geospatial land use database. Statistical dependencies between land cover and land use are explicitly modelled as pair-wise potentials. Thus, we obtain a consistent model, where the relations between land cover and land use are learned from representative training data. The approach is designed for input data based on aerial images. Experiments are performed on an urban test site. The experiments show the feasibility of the combination of both classification tasks into one overall approach and investigate the influence of the size of the superpixels on the classification result.
AB - This paper proposes a two-layer Conditional Random Field model for simultaneous classification of land cover and land use. Both classification tasks are integrated into a unified graphical model, which is reasonable due to the fact that land cover and land use exhibit strong contextual dependencies. In the CRF, we distinguish a land cover layer and a land use layer. Both layers differ with respect to the entities corresponding to the nodes and the classes to be distinguished. In the land cover layer, the nodes correspond to superpixels extracted from the image data, whereas in the land use layer the nodes correspond to objects of a geospatial land use database. Statistical dependencies between land cover and land use are explicitly modelled as pair-wise potentials. Thus, we obtain a consistent model, where the relations between land cover and land use are learned from representative training data. The approach is designed for input data based on aerial images. Experiments are performed on an urban test site. The experiments show the feasibility of the combination of both classification tasks into one overall approach and investigate the influence of the size of the superpixels on the classification result.
KW - Conditional Random Fields
KW - Contextual classification
KW - Land use classification
KW - Multi-layer
UR - http://www.scopus.com/inward/record.url?scp=84924248993&partnerID=8YFLogxK
U2 - 10.5194/isprsarchives-XL-3-17-2014
DO - 10.5194/isprsarchives-XL-3-17-2014
M3 - Conference article
AN - SCOPUS:84924248993
VL - 40
SP - 17
EP - 24
JO - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences - ISPRS Archives
JF - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences - ISPRS Archives
SN - 1682-1750
IS - 3
T2 - ISPRS Technical Commission III Symposium 2014
Y2 - 5 September 2014 through 7 September 2014
ER -