Dense 3D displacement vector fields for point cloud-based landslide monitoring
![Thumbnail](/bitstream/handle/20.500.11850/507673/Gojcic2021_Article_Dense3DDisplacementVectorField.pdf.jpg?sequence=5&isAllowed=y)
Open access
Datum
2021-12Typ
- Journal Article
Abstract
We propose a novel fully automated deformation analysis pipeline capable of estimating real 3D displacement vectors from point cloud data. Different from the traditional methods that establish displacements based on the proximity in the Euclidean space, our approach estimates dense 3D displacement vector fields by searching for corresponding points across the epochs in the space of 3D local feature descriptors. Due to this formulation, our method is also sensitive to motion and deformations that occur parallel to the underlying surface. By enabling efficient parallel processing, the proposed method can be applied to point clouds of arbitrary size. We compare our approach to the traditional methods on point cloud data of two landslides and show that while the traditional methods often underestimate the displacements, our method correctly estimates full 3D displacement vectors. Mehr anzeigen
Persistenter Link
https://doi.org/10.3929/ethz-b-000507673Publikationsstatus
publishedExterne Links
Zeitschrift / Serie
LandslidesBand
Seiten / Artikelnummer
Verlag
SpringerThema
Deformation analysis; Point clouds; Deep learning; 3D displacement vector fieldOrganisationseinheit
03964 - Wieser, Andreas / Wieser, Andreas