Details
| Original language | English |
|---|---|
| Pages (from-to) | 479-484 |
| Number of pages | 6 |
| Journal | International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences - ISPRS Archives |
| Volume | 39 |
| Publication status | Published - 2012 |
| Event | 22nd Congress of the International Society for Photogrammetry and Remote Sensing, ISPRS 2012 - Melbourne, Australia Duration: 25 Aug 2012 → 1 Sept 2012 |
Abstract
The precise classification and reconstruction of crossroads from multiple aerial images is a challenging problem in remote sensing. We apply the Markov Random Fields (MRF) approach to this problem, a probabilistic model that can be used to consider context in classification. A simple appearance-based model is combined with a probabilistic model of the co-occurrence of class label at neighbouring image sites to distinguish up to 14 different classes that are relevant for scenes containing crossroads. The parameters of these models are learnt from training data. We use multiple overlap aerial images to derive a digital surface model (DSM) and a true orthophoto without moving cars. From the DSM and the orthophoto we derive feature vectors that are used in the classification. One of the features is a car confidence value that is supposed to support the classification when the road surface is occluded by static cars. Our approach is evaluated on a dataset of airborne photos of an urban area by a comparison of the results to reference data. Whereas the method has problems in distinguishing classes having a similar appearance, it is shown to produce promising results if a reduced set of classes is considered, yielding an overall classification accuracy of 74.8%.
Keywords
- Classification, Contextual, Crossroads, Markov random fields
ASJC Scopus subject areas
- Computer Science(all)
- Information Systems
- Social Sciences(all)
- Geography, Planning and Development
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
In: International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences - ISPRS Archives, Vol. 39, 2012, p. 479-484.
Research output: Contribution to journal › Conference article › Research › peer review
}
TY - JOUR
T1 - 3D classification of crossroads from multiple aerial images using Markov Random Fields
AU - Kosov, S.
AU - Rottensteiner, F.
AU - Heipke, C.
AU - Leitloff, J.
AU - Hinz, S.
PY - 2012
Y1 - 2012
N2 - The precise classification and reconstruction of crossroads from multiple aerial images is a challenging problem in remote sensing. We apply the Markov Random Fields (MRF) approach to this problem, a probabilistic model that can be used to consider context in classification. A simple appearance-based model is combined with a probabilistic model of the co-occurrence of class label at neighbouring image sites to distinguish up to 14 different classes that are relevant for scenes containing crossroads. The parameters of these models are learnt from training data. We use multiple overlap aerial images to derive a digital surface model (DSM) and a true orthophoto without moving cars. From the DSM and the orthophoto we derive feature vectors that are used in the classification. One of the features is a car confidence value that is supposed to support the classification when the road surface is occluded by static cars. Our approach is evaluated on a dataset of airborne photos of an urban area by a comparison of the results to reference data. Whereas the method has problems in distinguishing classes having a similar appearance, it is shown to produce promising results if a reduced set of classes is considered, yielding an overall classification accuracy of 74.8%.
AB - The precise classification and reconstruction of crossroads from multiple aerial images is a challenging problem in remote sensing. We apply the Markov Random Fields (MRF) approach to this problem, a probabilistic model that can be used to consider context in classification. A simple appearance-based model is combined with a probabilistic model of the co-occurrence of class label at neighbouring image sites to distinguish up to 14 different classes that are relevant for scenes containing crossroads. The parameters of these models are learnt from training data. We use multiple overlap aerial images to derive a digital surface model (DSM) and a true orthophoto without moving cars. From the DSM and the orthophoto we derive feature vectors that are used in the classification. One of the features is a car confidence value that is supposed to support the classification when the road surface is occluded by static cars. Our approach is evaluated on a dataset of airborne photos of an urban area by a comparison of the results to reference data. Whereas the method has problems in distinguishing classes having a similar appearance, it is shown to produce promising results if a reduced set of classes is considered, yielding an overall classification accuracy of 74.8%.
KW - Classification
KW - Contextual
KW - Crossroads
KW - Markov random fields
UR - http://www.scopus.com/inward/record.url?scp=84924298864&partnerID=8YFLogxK
U2 - 10.5194/isprsarchives-XXXIX-B3-479-2012
DO - 10.5194/isprsarchives-XXXIX-B3-479-2012
M3 - Conference article
AN - SCOPUS:84924298864
VL - 39
SP - 479
EP - 484
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
T2 - 22nd Congress of the International Society for Photogrammetry and Remote Sensing, ISPRS 2012
Y2 - 25 August 2012 through 1 September 2012
ER -