eprintid: 37493
rev_number: 21
eprint_status: archive
userid: 8461
dir: disk0/00/03/74/93
datestamp: 2025-10-31 10:06:56
lastmod: 2025-11-05 08:25:35
status_changed: 2025-10-31 10:06:56
type: conferenceObject
metadata_visibility: show
creators_name: Weiser, Hannah
creators_name: Albert, William
creators_name: Höfle, Bernhard
title: Non-rigid registration of wind-affected terrestrial laser scanning point clouds of trees using deep learning
subjects: ddc-550
divisions: i-120700
pres_type: speech
keywords: Virtual laser scanning, Non-rigid registration, LiDAR Simulation, Wind effects, 3DGeo Research Group
cterms_swd: Deep Learning
cterms_swd: Terrestrisches Laserscanning
cterms_swd: Punktwolke
cterms_swd: Data quality
cterms_swd: Lidar
cterms_swd: Simulation
cterms_swd: Vegetation
note: Es handelt sich nur um den Abstract des Vortrages
abstract: Multi-station terrestrial laser scanning (TLS) is widely used to measure important forest variables. Wind effects like branch duplication remain a significant data quality issue in TLS point clouds and can lead to substantial errors in subsequent processing steps. Although scanning in windless conditions is recommended, it is not always practical.
The objective of this study is to present a method to transform wind-affected TLS point clouds into possible windless point cloud versions. Our method integrates recent deep learning (DL) models for the task of non-rigid registration, i.e., estimation of a displacement field.
To generate test data, we use virtual laser scanning (VLS) of dynamic scenes (VLS-4D): We simulate multi-station TLS acquisitions in HELIOS++ with each station capturing a dynamic tree model at a different timestamp. Knowing the exact movements of the virtual trees, we compute reference correspondences and respective displacement fields. We evaluate two pre-trained DL methods and a non-learned model-based method on the multi-view VLS-4D dataset. Performance is assessed by comparing estimated and reference displacement fields. In addition, we compare registered windless point clouds to truly windless VLS point clouds and evaluate the method on a real-world tree point cloud.
The strength of our approach is the validation using VLS. The manual generation of reference displacements in real-world data is error-prone, time-consuming and therefore not feasible for larger datasets. Our validation method takes procedurally generated and animated tree models as input, from which we compute error-free reference automatically. Preliminary results are promising and suggest that non-rigid registration enhances state-of-the-art registration and filtering workflows. This will improve the accuracy of subsequent processing tasks such as leaf-wood separation, quantitative structure modelling, and leaf area estimation.
date: 2025
id_scheme: DOI
id_number: 10.11588/heidok.00037493
own_urn: urn:nbn:de:bsz:16-heidok-374936
language: eng
bibsort: WEISERHANNNONRIGIDRE2025
full_text_status: public
place_of_pub: Québec City, QC, Canada
event_title: Silvilaser 2025
event_location: Québec City, QC, Canada
event_dates: 29 September - 3 October 2025
citation:   Weiser, Hannah ; Albert, William ; Höfle, Bernhard  (2025) Non-rigid registration of wind-affected terrestrial laser scanning point clouds of trees using deep learning.  [Conference Item]     
document_url: https://archiv.ub.uni-heidelberg.de/volltextserver/37493/13/Weiser_Non-rigid_registration_2025.pdf