2021
DOI: 10.5194/isprs-annals-viii-4-w2-2021-45-2021
|View full text |Cite
|
Sign up to set email alerts
|

Unlocking Point Cloud Potential: Fusing MLS Point Clouds With Semantic 3d Building Models While Considering Uncertainty

Abstract: Abstract. Throughout the years, semantic 3D city models have been created to depict 3D spatial phenomenon. Recently, an increasing number of mobile laser scanning (MLS) units yield terrestrial point clouds at an unprecedented level. Both dataset types often depict the same 3D spatial phenomenon differently, thus their fusion should increase the quality of the captured 3D spatial phenomenon. Yet, each dataset has modality-dependent uncertainties that hinder their immediate fusion. Therefore, we present a method… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1

Citation Types

0
2
0

Year Published

2022
2022
2024
2024

Publication Types

Select...
5

Relationship

1
4

Authors

Journals

citations
Cited by 5 publications
(2 citation statements)
references
References 24 publications
(40 reference statements)
0
2
0
Order By: Relevance
“…A good example of such a data interdependence is explained succinctly in (Tuttas et al, 2015), where an IFC model is compared against a point cloud model for monitoring construction progress. Another example of the need for data interoperability is shown in (Wysocki et al, 2021) where data from MLS point cloud is combined with semantic city models to improve the quality of 3D data capture.…”
Section: 2mentioning
confidence: 99%
“…A good example of such a data interdependence is explained succinctly in (Tuttas et al, 2015), where an IFC model is compared against a point cloud model for monitoring construction progress. Another example of the need for data interoperability is shown in (Wysocki et al, 2021) where data from MLS point cloud is combined with semantic city models to improve the quality of 3D data capture.…”
Section: 2mentioning
confidence: 99%
“…This, in turn, allows us to create buffers around building footprints extracted from vector GIS datasets (e.g., CityGML building models or OpenStreetMap (OSM) buildings). This ensures to reject a significant proportion of the point clouds and cluster the building-related points per building object, while addressing global point positioning inaccuracies (Wysocki et al, 2021b). Alternatively, when point clouds are not georeferenced or GIS datasets are unavailable, existing benchmark points, annotated as buildings, can be used as a pre-cluster for fac ¸ade-related points.…”
Section: Creating An Extended Benchmark Datasetmentioning
confidence: 99%