Details
| Original language | English |
|---|---|
| Title of host publication | 2012 IAPR Workshop on Pattern Recognition in Remote Sensing, PRRS 2012 |
| Publication status | Published - 2012 |
| Event | 2012 IAPR Workshop on Pattern Recognition in Remote Sensing, PRRS 2012 - Tsukuba Science City, Japan Duration: 11 Nov 2012 → 11 Nov 2012 |
Publication series
| Name | 2012 IAPR Workshop on Pattern Recognition in Remote Sensing, PRRS 2012 |
|---|
Abstract
We apply Conditional Random Fields for the classification of scenes containing crossroads, using a simple appearance-based model in combination with a probabilistic model of the co-occurrence of class labels at neighbouring image sites. We use multiple overlap aerial images to derive a digital surface model and a true orthophoto without dynamic objects such as cars. An evaluation on an urban data set of aerial images delivers promising results.
ASJC Scopus subject areas
- Computer Science(all)
- Computer Vision and Pattern Recognition
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
2012 IAPR Workshop on Pattern Recognition in Remote Sensing, PRRS 2012. 2012. 6398312 (2012 IAPR Workshop on Pattern Recognition in Remote Sensing, PRRS 2012).
Research output: Chapter in book/report/conference proceeding › Conference contribution › Research › peer review
}
TY - GEN
T1 - 3D classification of crossroads from multiple aerial images using conditional random fields
AU - Kosov, Sergey
AU - Rottensteiner, Franz
AU - Heipke, Christian
PY - 2012
Y1 - 2012
N2 - We apply Conditional Random Fields for the classification of scenes containing crossroads, using a simple appearance-based model in combination with a probabilistic model of the co-occurrence of class labels at neighbouring image sites. We use multiple overlap aerial images to derive a digital surface model and a true orthophoto without dynamic objects such as cars. An evaluation on an urban data set of aerial images delivers promising results.
AB - We apply Conditional Random Fields for the classification of scenes containing crossroads, using a simple appearance-based model in combination with a probabilistic model of the co-occurrence of class labels at neighbouring image sites. We use multiple overlap aerial images to derive a digital surface model and a true orthophoto without dynamic objects such as cars. An evaluation on an urban data set of aerial images delivers promising results.
UR - http://www.scopus.com/inward/record.url?scp=84873101801&partnerID=8YFLogxK
U2 - 10.1109/PPRS.2012.6398312
DO - 10.1109/PPRS.2012.6398312
M3 - Conference contribution
AN - SCOPUS:84873101801
SN - 9781467349628
T3 - 2012 IAPR Workshop on Pattern Recognition in Remote Sensing, PRRS 2012
BT - 2012 IAPR Workshop on Pattern Recognition in Remote Sensing, PRRS 2012
T2 - 2012 IAPR Workshop on Pattern Recognition in Remote Sensing, PRRS 2012
Y2 - 11 November 2012 through 11 November 2012
ER -