Paper published in a journal (Scientific congresses and symposiums)
TESSERAE3D: A benchmark for tesserae semantic segmentation in 3D point clouds
Kharroubi, Abderrazzaq; Van Wersch, Line; Billen, Roland et al.
2021In ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, V-2-2021, p. 121–128
 

Files


Full Text
isprs-annals-V-2-2021-121-2021.pdf
Publisher postprint (1.86 MB)
TESSERAE3D: A BENCHMARK FOR TESSERAE SEMANTIC SEGMENTATION IN 3D POINT CLOUDS
Download

All documents in ORBi are protected by a user license.

Send to



Details



Keywords :
3D Point Cloud; Tesserae; Semantic Segmentation; Dataset; Machine Learning
Abstract :
[en] 3D point cloud of mosaic tesserae is used by heritage researchers, restorers, and archaeologists for digital investigations. Information extraction, pattern analysis, and semantic assignment are necessary to complement geometric information. Automated processes that can speed up the task are highly sought after, especially new supervised approaches. However, the availability of labeled data necessary for training supervised learning models is a significant constraint. This paper introduces Tesserae3D, a 3D point cloud benchmark dataset for training and evaluating machine learning models, applied to mosaic tesserae segmentation. It is a publicly available, very high density and colored dataset, accompanied by a standard multi-class semantic segmentation baseline. It consists of about 502 million points and contains 11 semantic classes covering a wide range of tesserae types. We propose a semantic segmentation baseline building on radiometric and covariance features fed to ensemble learning methods. The results delineate an achievable 89% F1 score and are made available under https://github.com/akharroubi/Tesserae3D, providing a simple interface to improve the score based on feedback from the research community.
Research center :
Sphères - SPHERES
Disciplines :
Computer science
Earth sciences & physical geography
Author, co-author :
Kharroubi, Abderrazzaq  ;  Université de Liège - ULiège > Département de géographie > Unité de Géomatique - Topographie et géométrologie
Van Wersch, Line  ;  Université de Liège - ULiège > Département des sciences historiques > Archéologie médiévale et post-médiévale
Billen, Roland  ;  Université de Liège - ULiège > Département de géographie > Unité de Géomatique - Topographie et géométrologie
Poux, Florent  ;  Université de Liège - ULiège > Département de géographie > Unité de Géomatique - Topographie et géométrologie
Language :
English
Title :
TESSERAE3D: A benchmark for tesserae semantic segmentation in 3D point clouds
Alternative titles :
[en] TESSERAE3D : Une comparaison pour la segmentation sémantique des tesselles dans les nuages de points 3D
Publication date :
17 June 2021
Event name :
XXIV ISPRS Congress 2021
Event organizer :
ISPRS
Event place :
Nice, France
Event date :
Du 05 juillet 2021 au 09 juillet 2021
Audience :
International
Journal title :
ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences
ISSN :
2194-9042
eISSN :
2194-9050
Publisher :
Copernicus, Goettingen, Germany
Volume :
V-2-2021
Pages :
121–128
Funders :
F.R.S.-FNRS - Fonds de la Recherche Scientifique [BE]
Available on ORBi :
since 28 July 2021

Statistics


Number of views
138 (17 by ULiège)
Number of downloads
106 (12 by ULiège)

Scopus citations®
 
1
Scopus citations®
without self-citations
1
OpenCitations
 
0

Bibliography


Similar publications



Contact ORBi