Details
| Original language | English |
|---|---|
| Pages (from-to) | 17-30 |
| Number of pages | 14 |
| Journal | Journal of photogrammetry, remote sensing and geoinformation science |
| Volume | 85 |
| Issue number | 1 |
| Early online date | 21 Feb 2017 |
| Publication status | Published - Feb 2017 |
Abstract
We propose a new method for the context-based classification of point clouds from stereo images using Conditional Random Fields (CRF). The classification is based on segments as nodes for the CRF. The segmentation is conducted on the image and is transferred to the 3D point cloud obtained by image matching. This allows the computation of 3D features additionally to the image features as well as the definition of realistic adjacencies between the segments in object space. We also propose a variant of the contrast-sensitive Potts model that is tailored for the contextual classification of point cloud segments. The evaluation of our method is performed on stereo sequences of a benchmark dataset, recorded in an urban area, and yields results with an overall accuracy of more than 90%. Moreover, we can show that the consideration of contextual information during the classification leads to an improvement of the overall accuracy.
Keywords
- 3D reconstruction, Classification, Conditional random fields, Mobile mapping, Segmentation, Stereo images
ASJC Scopus subject areas
- Social Sciences(all)
- Geography, Planning and Development
- Physics and Astronomy(all)
- Instrumentation
- Earth and Planetary Sciences(all)
- Earth and Planetary Sciences (miscellaneous)
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
In: Journal of photogrammetry, remote sensing and geoinformation science, Vol. 85, No. 1, 02.2017, p. 17-30.
Research output: Contribution to journal › Article › Research › peer review
}
TY - JOUR
T1 - Classification of Stereo Images from Mobile Mapping Data Using Conditional Random Fields
AU - Coenen, Max
AU - Rottensteiner, Franz
AU - Heipke, Christian
N1 - Publisher Copyright: © 2017 Deutsche Gesellschaft für Photogrammetrie, Fernerkundung und Geoinformation (DGPF) e.V. Copyright: Copyright 2017 Elsevier B.V., All rights reserved.
PY - 2017/2
Y1 - 2017/2
N2 - We propose a new method for the context-based classification of point clouds from stereo images using Conditional Random Fields (CRF). The classification is based on segments as nodes for the CRF. The segmentation is conducted on the image and is transferred to the 3D point cloud obtained by image matching. This allows the computation of 3D features additionally to the image features as well as the definition of realistic adjacencies between the segments in object space. We also propose a variant of the contrast-sensitive Potts model that is tailored for the contextual classification of point cloud segments. The evaluation of our method is performed on stereo sequences of a benchmark dataset, recorded in an urban area, and yields results with an overall accuracy of more than 90%. Moreover, we can show that the consideration of contextual information during the classification leads to an improvement of the overall accuracy.
AB - We propose a new method for the context-based classification of point clouds from stereo images using Conditional Random Fields (CRF). The classification is based on segments as nodes for the CRF. The segmentation is conducted on the image and is transferred to the 3D point cloud obtained by image matching. This allows the computation of 3D features additionally to the image features as well as the definition of realistic adjacencies between the segments in object space. We also propose a variant of the contrast-sensitive Potts model that is tailored for the contextual classification of point cloud segments. The evaluation of our method is performed on stereo sequences of a benchmark dataset, recorded in an urban area, and yields results with an overall accuracy of more than 90%. Moreover, we can show that the consideration of contextual information during the classification leads to an improvement of the overall accuracy.
KW - 3D reconstruction
KW - Classification
KW - Conditional random fields
KW - Mobile mapping
KW - Segmentation
KW - Stereo images
UR - http://www.scopus.com/inward/record.url?scp=85013799278&partnerID=8YFLogxK
U2 - 10.1007/s41064-017-0004-5
DO - 10.1007/s41064-017-0004-5
M3 - Article
AN - SCOPUS:85013799278
VL - 85
SP - 17
EP - 30
JO - Journal of photogrammetry, remote sensing and geoinformation science
JF - Journal of photogrammetry, remote sensing and geoinformation science
SN - 1432-8364
IS - 1
ER -