Details
| Original language | English |
|---|---|
| Pages (from-to) | 151-159 |
| Number of pages | 9 |
| Journal | ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences |
| Volume | 5 |
| Issue number | 2 |
| Publication status | Published - 3 Aug 2020 |
Abstract
In the present work, an uncertainty-driven geometry-based regularisation for the task of dense stereo matching is presented. The objective of the regularisation is the reduction of ambiguities in the depth reconstruction process, which exist due to the ill-posed nature of this task. Based on cost and uncertainty information computed beforehand, pixels are selected, whose depth information can be determined correctly with a high probability. This depth information assumed to be of high confidence is initially used to construct a triangle mesh, which is interpreted as surface approximation of the imaged scene and allows to propagate the confident depth information of the triangle vertices within local neighbourhoods. The proposed method further computes confidence scores for propagated depth estimates, which are used to fuse this depth information with the previously computed cost information, introducing a regularisation into the data term of global optimisation methods. Furthermore, based on the propagated depth information the local smoothness assumption of global optimisation methods is adjusted. Instead of fronto-parallel planes, the method presumes planes, which are parallel to the propagated depth information. The performance of the proposed regularisation approach is evaluated in combination with a global optimisation method. For a quantitative and qualitative evaluation two commonly employed and well-established stereo datasets are used. The proposed method shows significant improvements in accuracy on both datasets and for two different cost computation methods. Especially in unstructured areas, artefacts in the disparity maps are reduced.
Keywords
- Confidence, Dense Image Matching, Depth Reconstruction, Regularisation, Triangle Mesh
ASJC Scopus subject areas
- Earth and Planetary Sciences(all)
- Earth and Planetary Sciences (miscellaneous)
- Environmental Science(all)
- Environmental Science (miscellaneous)
- Physics and Astronomy(all)
- Instrumentation
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
In: ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, Vol. 5, No. 2, 03.08.2020, p. 151-159.
Research output: Contribution to journal › Conference article › Research › peer review
}
TY - JOUR
T1 - Geometry-Based Regularisation for Dense Image Matching via Uncertainty-Driven Depth Propagation
AU - Höllmann, M.
AU - Mehltretter, M.
AU - Heipke, C.
N1 - Funding information: This work was supported by the MOBILISE initiative of the Leibniz University Hannover and TU Braunschweig and the German Research Foundation (DFG) as a part of the Research Training Group i.c.sens [GRK2159].
PY - 2020/8/3
Y1 - 2020/8/3
N2 - In the present work, an uncertainty-driven geometry-based regularisation for the task of dense stereo matching is presented. The objective of the regularisation is the reduction of ambiguities in the depth reconstruction process, which exist due to the ill-posed nature of this task. Based on cost and uncertainty information computed beforehand, pixels are selected, whose depth information can be determined correctly with a high probability. This depth information assumed to be of high confidence is initially used to construct a triangle mesh, which is interpreted as surface approximation of the imaged scene and allows to propagate the confident depth information of the triangle vertices within local neighbourhoods. The proposed method further computes confidence scores for propagated depth estimates, which are used to fuse this depth information with the previously computed cost information, introducing a regularisation into the data term of global optimisation methods. Furthermore, based on the propagated depth information the local smoothness assumption of global optimisation methods is adjusted. Instead of fronto-parallel planes, the method presumes planes, which are parallel to the propagated depth information. The performance of the proposed regularisation approach is evaluated in combination with a global optimisation method. For a quantitative and qualitative evaluation two commonly employed and well-established stereo datasets are used. The proposed method shows significant improvements in accuracy on both datasets and for two different cost computation methods. Especially in unstructured areas, artefacts in the disparity maps are reduced.
AB - In the present work, an uncertainty-driven geometry-based regularisation for the task of dense stereo matching is presented. The objective of the regularisation is the reduction of ambiguities in the depth reconstruction process, which exist due to the ill-posed nature of this task. Based on cost and uncertainty information computed beforehand, pixels are selected, whose depth information can be determined correctly with a high probability. This depth information assumed to be of high confidence is initially used to construct a triangle mesh, which is interpreted as surface approximation of the imaged scene and allows to propagate the confident depth information of the triangle vertices within local neighbourhoods. The proposed method further computes confidence scores for propagated depth estimates, which are used to fuse this depth information with the previously computed cost information, introducing a regularisation into the data term of global optimisation methods. Furthermore, based on the propagated depth information the local smoothness assumption of global optimisation methods is adjusted. Instead of fronto-parallel planes, the method presumes planes, which are parallel to the propagated depth information. The performance of the proposed regularisation approach is evaluated in combination with a global optimisation method. For a quantitative and qualitative evaluation two commonly employed and well-established stereo datasets are used. The proposed method shows significant improvements in accuracy on both datasets and for two different cost computation methods. Especially in unstructured areas, artefacts in the disparity maps are reduced.
KW - Confidence
KW - Dense Image Matching
KW - Depth Reconstruction
KW - Regularisation
KW - Triangle Mesh
UR - http://www.scopus.com/inward/record.url?scp=85091079028&partnerID=8YFLogxK
U2 - 10.5194/isprs-annals-v-2-2020-151-2020
DO - 10.5194/isprs-annals-v-2-2020-151-2020
M3 - Conference article
VL - 5
SP - 151
EP - 159
JO - ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences
JF - ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences
SN - 2194-9042
IS - 2
ER -