EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Segmentation of 3D Point Clouds of Heritage Buildings Using Edge Detection and Supervoxel-Based Topology

Santiago Salamanca iD, Pilar Merchán iD, Alejandro Espacio iD, Emiliano Pérez iD, María José Merchán iD

Sensors · 06.07.2024 · 24 (13) · 4390

DOI: 10.3390/s24134390 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 06.07.2024. Verfasst von Santiago Salamanca und 4 weiteren Autor:innen. Beteiligte Einrichtung: Departamento de Ingeniería Eléctrica, Electrónica y Automática, Escuela de Ingenierías Industriales, Universidad de Extremadura, Avda. Elvas s/n, 060…. Die Arbeit wurde bisher 12-mal zitiert (Crossref) und nennt 47 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Agencia Estatal de Investigación, Government of Extremadura, Consejería de Economía, Ciencia y Agenda Digital (Junta de Extremadura).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This paper presents a novel segmentation algorithm specially developed for applications in 3D point clouds with high variability and noise, particularly suitable for heritage building 3D data. The method can be categorized within the segmentation procedures based on edge detection. In addition, it uses a graph-based topological structure generated from the supervoxelization of the 3D point clouds, which is used to make the closure of the edge points and to define the different segments. The algorithm provides a valuable tool for generating results that can be used in subsequent classification tasks and broader computer applications dealing with 3D point clouds. One of the characteristics of this segmentation method is that it is unsupervised, which makes it particularly advantageous for heritage applications where labelled data is scarce. It is also easily adaptable to different edge point detection and supervoxelization algorithms. Finally, the results show that the 3D data can be segmented into different architectural elements, which is important for further classification or recognition. Extensive testing on real data from historic buildings demonstrated the effectiveness of the method. The results show superior performance compared to three other segmentation methods, both globally and in the segmentation of planar and curved zones of historic buildings.

Schlagwörter

Stichwörter der Autor:innen

3D point cloudsedge detectionheritage buildingslaser scannersegmentationsupervoxels

Autor:innen und Institutionen

  • Departamento de Ingeniería Eléctrica, Electrónica y Automática, Escuela de Ingenierías Industriales, Universidad de Extremadura, Avda. Elvas s/n, 06006 Badajoz, Spain.
  • Departamento de Expresión Gráfica, Escuela de Ingenierías Industriales, Universidad de Extremadura, Avda. Elvas s/n, 06006 Badajoz, Spain.
  • Departamento de Didáctica de las Ciencias Sociales, Lengua y Literatura, Facultad de Educación y Psicología, Universidad de Extremadura, Avda. Elvas s/n, 06006 Badajoz, Spain.

ORCID-Profile: Santiago Salamanca, Pilar Merchán, Alejandro Espacio, Emiliano Pérez, María José Merchán

Förderung

  • Agencia Estatal de Investigación
  • Government of Extremadura
  • Consejería de Economía, Ciencia y Agenda Digital (Junta de Extremadura)

Zitieren

APA

Salamanca, S., Merchán, P., Espacio, A., Pérez, E., & Merchán, M. J. (2024). Segmentation of 3D Point Clouds of Heritage Buildings Using Edge Detection and Supervoxel-Based Topology. Sensors, 24(13), 4390. https://doi.org/10.3390/s24134390

Vancouver

Salamanca S, Merchán P, Espacio A, Pérez E, Merchán MJ. Segmentation of 3D Point Clouds of Heritage Buildings Using Edge Detection and Supervoxel-Based Topology. Sensors. 2024;24(13):4390. doi:10.3390/s24134390

BibTeX
@article{Salamanca2024,
  author = {Salamanca, Santiago and Merchán, Pilar and Espacio, Alejandro and Pérez, Emiliano and Merchán, María José},
  title = {Segmentation of 3D Point Clouds of Heritage Buildings Using Edge Detection and Supervoxel-Based Topology},
  journal = {Sensors},
  year = {2024},
  volume = {24},
  number = {13},
  pages = {4390},
  doi = {10.3390/s24134390}
}
Kostenlos starten →