Details
| Original language | English |
|---|---|
| Title of host publication | 2010 IAPR Workshop on Pattern Recognition in Remote Sensing, PRRS 2010 |
| Publication status | Published - 2010 |
| Event | 6th IAPR Workshop on Pattern Recognition in Remote Sensing, PRRS 2010 - Istanbul, Turkey Duration: 22 Aug 2010 → 22 Aug 2010 |
Publication series
| Name | 2010 IAPR Workshop on Pattern Recognition in Remote Sensing, PRRS 2010 |
|---|
Abstract
Land cover classification plays a key role for various geo-based applications. Many approaches for the classification of remote sensing data assume the features of neighboring image sites to be conditionally independent. However, using spatial and temporal context information may enhance classification accuracy. Conditional Random Fields (CRF) have the ability to model dependencies not only between the class labels of neighboring image sites, but also between the labels and the image features. In this work we present a novel approach for multitemporal classification in high resolution satellite imagery using CRF that is based on an extension of the CRF model by a time-dependant component. The potential of our approach is demonstrated using a set of two Ikonos and one RapidEye scenes of a rural area in Germany.
ASJC Scopus subject areas
- Computer Science(all)
- Computer Vision and Pattern Recognition
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
2010 IAPR Workshop on Pattern Recognition in Remote Sensing, PRRS 2010. 2010. 5742800 (2010 IAPR Workshop on Pattern Recognition in Remote Sensing, PRRS 2010).
Research output: Chapter in book/report/conference proceeding › Conference contribution › Research › peer review
}
TY - GEN
T1 - Classification of multitemporal remote sensing data using conditional Random fields
AU - Hoberg, Thorsten
AU - Rottensteiner, Franz
AU - Heipke, Christian
PY - 2010
Y1 - 2010
N2 - Land cover classification plays a key role for various geo-based applications. Many approaches for the classification of remote sensing data assume the features of neighboring image sites to be conditionally independent. However, using spatial and temporal context information may enhance classification accuracy. Conditional Random Fields (CRF) have the ability to model dependencies not only between the class labels of neighboring image sites, but also between the labels and the image features. In this work we present a novel approach for multitemporal classification in high resolution satellite imagery using CRF that is based on an extension of the CRF model by a time-dependant component. The potential of our approach is demonstrated using a set of two Ikonos and one RapidEye scenes of a rural area in Germany.
AB - Land cover classification plays a key role for various geo-based applications. Many approaches for the classification of remote sensing data assume the features of neighboring image sites to be conditionally independent. However, using spatial and temporal context information may enhance classification accuracy. Conditional Random Fields (CRF) have the ability to model dependencies not only between the class labels of neighboring image sites, but also between the labels and the image features. In this work we present a novel approach for multitemporal classification in high resolution satellite imagery using CRF that is based on an extension of the CRF model by a time-dependant component. The potential of our approach is demonstrated using a set of two Ikonos and one RapidEye scenes of a rural area in Germany.
UR - http://www.scopus.com/inward/record.url?scp=79955539578&partnerID=8YFLogxK
U2 - 10.1109/PRRS.2010.5742800
DO - 10.1109/PRRS.2010.5742800
M3 - Conference contribution
AN - SCOPUS:79955539578
SN - 9781424472574
T3 - 2010 IAPR Workshop on Pattern Recognition in Remote Sensing, PRRS 2010
BT - 2010 IAPR Workshop on Pattern Recognition in Remote Sensing, PRRS 2010
T2 - 6th IAPR Workshop on Pattern Recognition in Remote Sensing, PRRS 2010
Y2 - 22 August 2010 through 22 August 2010
ER -