Automatic Detection of Windows Reflection or Transparency Pollution in TLS Acquisitions

Simple item page
dc.contributor.authorBadalyan, Edgaren_US
dc.contributor.authorSchenkel, Arnauden_US
dc.contributor.authorDebeir, Olivieren_US
dc.contributor.editorBucciero, Albertoen_US
dc.contributor.editorFanini, Brunoen_US
dc.contributor.editorGraf, Holgeren_US
dc.contributor.editorPescarin, Sofiaen_US
dc.contributor.editorRizvic, Selmaen_US
dc.date.accessioned2023-09-02T07:44:30Z
dc.date.available2023-09-02T07:44:30Z
dc.date.issued2023
dc.description.abstractThree-dimensional acquisitions have been more and more used in recent years, for multiple applications, such as cultural heritage preservation. When these point clouds are generated through laser scanning, transparent and/or reflective objects such as windows can generate inexact or undesirable data. These must be cleaned up by a human, which is often time-consuming and requires experience. This work provides an insight on some methods that can be used to automate this task. It investigates the usage of Mask R-CNN with intensity images in equirectangular projections. The huge images are tiled into squares of 2048x2048 pixels for both training and prediction. The model has good performances on the test and validation sets to handle both types of problems; but also to manage the presence of a mirror in a scene.en_US
dc.description.sectionheadersSimulation in CH
dc.description.seriesinformationEurographics Workshop on Graphics and Cultural Heritage
dc.identifier.doi10.2312/gch.20231163
dc.identifier.isbn978-3-03868-217-2
dc.identifier.issn2312-6124
dc.identifier.pages89-92
dc.identifier.pages4 pages
dc.identifier.urihttps://doi.org/10.2312/gch.20231163
dc.identifier.urihttps://diglib.eg.org:443/handle/10.2312/gch20231163
dc.publisherThe Eurographics Associationen_US
dc.rightsAttribution 4.0 International License
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/
dc.subjectCCS Concepts: Computing methodologies → Object detection; Image segmentation
dc.subjectComputing methodologies → Object detection
dc.subjectImage segmentation
dc.titleAutomatic Detection of Windows Reflection or Transparency Pollution in TLS Acquisitionsen_US
Files
Original bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
089-092.pdf
Size:
10.95 MB
Format:
Adobe Portable Document Format
Download
Collections
GCH 2023 - Eurographics Workshop on Graphics and Cultural Heritage