Detecting Historical Terrain Anomalies With UAV-LiDAR Data Using Spline-Approximation and Support Vector Machines

DC FieldValueLanguage
dc.contributor.authorStorch, Marcel
dc.contributor.authorde Lange, Norbert
dc.contributor.authorJarmer, Thomas
dc.contributor.authorWaske, Bjorn
dc.date.accessioned2023-07-12T06:53:47Z-
dc.date.available2023-07-12T06:53:47Z-
dc.date.issued2023
dc.identifier.issn1939-1404
dc.identifier.urihttp://osnascholar.ub.uni-osnabrueck.de/handle/unios/71824-
dc.description.abstractThe documentation of historical remains and cultural heritage is of great importance to preserve historical knowledge. Many studies use low-resolution airplane-based laser scanning and manual interpretation for this purpose. In this study, a concept to automatically detect terrain anomalies in a historical conflict landscape using high-resolution UAV-LiDAR data was developed. We applied different ground filter algorithms and included a spline-based approximation step in order to improve the removal of low vegetation. Due to the absence of comprehensive labeled training data, a one-class support vector machine algorithm was used in an unsupervised manner in order to automatically detect the terrain anomalies. We applied our approach in a study site with different densities of low vegetation. The morphological ground filter was the most suitable when dense near-ground vegetation is present. However, with the use of the spline-based processing step, all filters used could be significantly improved in terms of the F1-score of the classification results. It increased by up to 42% points in the area with dense low vegetation and by up to 14% points in the area with sparse low vegetation. The completeness (recall) reached maximum values of 0.8 and 1.0, respectively, when taking into account the results leading to the highest F1-score for each filter. Therefore, our concept can support on-site field prospection.
dc.description.sponsorshipDeutsche Forschungsgemeinschaft (DFG); Open Access Publishing Fund of Osnabrueck University; This work was supported by Deutsche Forschungsgemeinschaft (DFG) and Open Access Publishing Fund of Osnabrueck University.
dc.language.isoen
dc.publisherIEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
dc.relation.ispartofIEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING
dc.subjectAIRBORNE
dc.subjectAUTOMATIC DETECTION
dc.subjectCultural differences
dc.subjectEngineering
dc.subjectEngineering, Electrical & Electronic
dc.subjectEXTRACTION
dc.subjectFiltering algorithms
dc.subjectGeography, Physical
dc.subjectHistorical terrain anomalies
dc.subjectImaging Science & Photographic Technology
dc.subjectINTERPOLATION
dc.subjectLANDSCAPE
dc.subjectLaser radar
dc.subjectmachine learning
dc.subjectONE-CLASS CLASSIFICATION
dc.subjectPhysical Geography
dc.subjectREGULARIZED SPLINE
dc.subjectRemote Sensing
dc.subjectSEGMENTATION
dc.subjectsplines
dc.subjectSplines (mathematics)
dc.subjectSupport vector machines
dc.subjectSURFACE
dc.subjectTENSION
dc.subjectUAV-LiDAR
dc.subjectVegetation mapping
dc.titleDetecting Historical Terrain Anomalies With UAV-LiDAR Data Using Spline-Approximation and Support Vector Machines
dc.typejournal article
dc.identifier.doi10.1109/JSTARS.2023.3259200
dc.identifier.isiISI:000964706600005
dc.description.volume16
dc.description.startpage3158
dc.description.endpage3173
dc.contributor.orcidhttp://orcid.org/0000-0001-5726-6297
dc.contributor.orcidhttp://orcid.org/0000-0002-2586-3748
dc.contributor.orcidhttp://orcid.org/0000-0002-4652-1640
dc.identifier.eissn2151-1535
dc.publisher.place445 HOES LANE, PISCATAWAY, NJ 08855-4141 USA
dcterms.isPartOf.abbreviationIEEE J. Sel. Top. Appl. Earth Observ. Remote Sens.
dcterms.oaStatusgold
local.import.remainsaffiliations : University Osnabruck
local.import.remainsweb-of-science-index : Science Citation Index Expanded (SCI-EXPANDED)
crisitem.author.deptFB 06 - Mathematik/Informatik-
crisitem.author.deptFB 06 - Mathematik/Informatik-
crisitem.author.deptFB 06 - Mathematik/Informatik-
crisitem.author.deptidfb06-
crisitem.author.deptidfb06-
crisitem.author.deptidfb06-
crisitem.author.orcid0000-0002-4652-1640-
crisitem.author.parentorgUniversität Osnabrück-
crisitem.author.parentorgUniversität Osnabrück-
crisitem.author.parentorgUniversität Osnabrück-
crisitem.author.netidLaNo930-
crisitem.author.netidJaTh054-
crisitem.author.netidWaBj345-
Show simple item record

Page view(s)

4
Last Week
0
Last month
3
checked on May 27, 2024

Google ScholarTM

Check

Altmetric