F2S3: Robustified determination of 3D displacement vector fields using deep learning


Date

2020-04

Publication Type

Journal Article

ETH Bibliography

yes

Citations

Altmetric

Data

Abstract

Areal deformation monitoring based on point clouds can be a very valuable alternative to the established point-based monitoring techniques, especially for deformation monitoring of natural scenes. However, established deformation analysis approaches for point clouds do not necessarily expose the true 3D changes, because the correspondence between points is typically established naïvely. Recently, approaches to establish the correspondences in the feature space by using local feature descriptors that analyze the geometric peculiarities in the neighborhood of the interest points were proposed. However, the resulting correspondences are noisy and contain a large number of outliers. This impairs the direct applicability of these approaches for deformation monitoring. In this work, we propose Feature to Feature Supervoxel-based Spatial Smoothing (F2S3), a new deformation analysis method for point cloud data. In F2S3 we extend the recently proposed feature-based algorithms with a neural network based outlier detection, capable of classifying the putative pointwise correspondences into inliers and outliers based on the local context extracted from the supervoxels. We demonstrate the proposed method on two data sets, including a real case data set of a landslide located in the Swiss Alps. We show that while the traditional approaches, in this case, greatly underestimate the magnitude of the displacements, our method can correctly estimate the true 3D displacement vectors.

Publication status

published

Editor

Book title

Volume

14 (2)

Pages / Article No.

177 - 189

Publisher

De Gruyter

Event

Edition / version

Methods

Software

Geographic location

Date collected

Date created

Subject

Deformation monitoring; point clouds; neural networks; Local feature descriptors; outlier detection; displacement vectors; RANSAC

Organisational unit

03964 - Wieser, Andreas / Wieser, Andreas check_circle

Notes

Funding

Related publications and datasets