Classification of structural building damage grades from multi-temporal photogrammetric point clouds using a machine learning model trained on virtual laser scanning data
Automatic damage assessment by analysing UAV-derived 3D point clouds provides fast information on the damage situation after an earthquake. However, the assessment of different damage grades is challenging given the variety in damage characteristics and limited transferability of methods to other ge...
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Dokumenttyp: | Article (Journal) |
| Sprache: | Englisch |
| Veröffentlicht: |
August 2023
|
| In: |
International journal of applied earth observation and geoinformation
Year: 2023, Jahrgang: 122, Pages: 1-15 |
| ISSN: | 1872-826X |
| DOI: | 10.1016/j.jag.2023.103406 |
| Online-Zugang: | Verlag, lizenzpflichtig, Volltext: https://doi.org/10.1016/j.jag.2023.103406 Verlag, lizenzpflichtig, Volltext: https://www.sciencedirect.com/science/article/pii/S1569843223002303 
|
| Verfasserangaben: | Vivien Zahs, Katharina Anders, Julia Kohns, Alexander Stark, Bernhard Höfle |
MARC
| LEADER | 00000caa a2200000 c 4500 | ||
|---|---|---|---|
| 001 | 1853179108 | ||
| 003 | DE-627 | ||
| 005 | 20240307072759.0 | ||
| 007 | cr uuu---uuuuu | ||
| 008 | 230720s2023 xx |||||o 00| ||eng c | ||
| 024 | 7 | |a 10.1016/j.jag.2023.103406 |2 doi | |
| 035 | |a (DE-627)1853179108 | ||
| 035 | |a (DE-599)KXP1853179108 | ||
| 035 | |a (OCoLC)1425214898 | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rda | ||
| 041 | |a eng | ||
| 084 | |a 61 |2 sdnb | ||
| 100 | 1 | |a Zahs, Vivien |e VerfasserIn |0 (DE-588)1227935412 |0 (DE-627)1749138905 |4 aut | |
| 245 | 1 | 0 | |a Classification of structural building damage grades from multi-temporal photogrammetric point clouds using a machine learning model trained on virtual laser scanning data |c Vivien Zahs, Katharina Anders, Julia Kohns, Alexander Stark, Bernhard Höfle |
| 264 | 1 | |c August 2023 | |
| 300 | |b Illustrationen | ||
| 300 | |a 15 | ||
| 336 | |a Text |b txt |2 rdacontent | ||
| 337 | |a Computermedien |b c |2 rdamedia | ||
| 338 | |a Online-Ressource |b cr |2 rdacarrier | ||
| 500 | |a Online verfügbar: 15. Juli 2023, Artikelversion: 15. Juli 2023 | ||
| 500 | |a Gesehen am 20.07.2023 | ||
| 520 | |a Automatic damage assessment by analysing UAV-derived 3D point clouds provides fast information on the damage situation after an earthquake. However, the assessment of different damage grades is challenging given the variety in damage characteristics and limited transferability of methods to other geographic regions or data sources. We present a novel change-based approach to automatically assess multi-class building damage from real-world point clouds using a machine learning model trained on virtual laser scanning (VLS) data. Therein, we (1) identify object-specific point cloud-based change features, (2) extract changed building parts using k-means clustering, (3) train a random forest machine learning model with VLS data based on object-specific change features, and (4) use the classifier to assess building damage in real-world photogrammetric point clouds. We evaluate the classifier with respect to its capacity to classify three damage grades (heavy, extreme, destruction) in pre-event and post-event point clouds of an earthquake in L’Aquila (Italy). Using object-specific change features derived from bi-temporal point clouds, our approach is transferable with respect to multi-source input point clouds used for model training (VLS) and application (real-world photogrammetry). We further achieve geographic transferability by using simulated training data which characterises damage grades across different geographic regions. The model yields high multi-target classification accuracies (overall accuracy: 92.0%-95.1%). Classification performance improves only slightly when using real-world region-specific training data (< 3% higher overall accuracies). We consider our approach especially relevant for applications where timely information on the damage situation is required and sufficient real-world training data is not available. | ||
| 650 | 4 | |a 3D | |
| 650 | 4 | |a Change detection | |
| 650 | 4 | |a Damage classification | |
| 650 | 4 | |a Earthquake | |
| 650 | 4 | |a Natural hazards | |
| 650 | 4 | |a UAV | |
| 700 | 1 | |a Anders, Katharina |d 1990- |e VerfasserIn |0 (DE-588)1128842580 |0 (DE-627)883601109 |0 (DE-576)48610298X |4 aut | |
| 700 | 1 | |a Kohns, Julia |e VerfasserIn |4 aut | |
| 700 | 1 | |a Stark, Alexander |d 1975- |e VerfasserIn |0 (DE-588)138447268 |0 (DE-627)696634201 |0 (DE-576)250377330 |4 aut | |
| 700 | 1 | |a Höfle, Bernhard |e VerfasserIn |0 (DE-588)1019895403 |0 (DE-627)691049297 |0 (DE-576)358986753 |4 aut | |
| 773 | 0 | 8 | |i Enthalten in |t International journal of applied earth observation and geoinformation |d Amsterdam [u.a.] : Elsevier Science, 1999 |g 122(2023) vom: Aug., Artikel-ID 103406, Seite 1-15 |h Online-Ressource |w (DE-627)359784119 |w (DE-600)2097960-5 |w (DE-576)25927254X |x 1872-826X |7 nnas |a Classification of structural building damage grades from multi-temporal photogrammetric point clouds using a machine learning model trained on virtual laser scanning data |
| 773 | 1 | 8 | |g volume:122 |g year:2023 |g month:08 |g elocationid:103406 |g pages:1-15 |g extent:15 |a Classification of structural building damage grades from multi-temporal photogrammetric point clouds using a machine learning model trained on virtual laser scanning data |
| 787 | 0 | 8 | |i Forschungsdaten |a Zahs, Vivien |t Classification of structural building damage grades from multi-temporal photogrammetric point clouds using a machine learning model trained on virtual laser scanning data [Data and Source Code] |d Heidelberg : Universität, 2023 |h 1 Online-Ressource (7 Files) |w (DE-627)1853178365 |
| 856 | 4 | 0 | |u https://doi.org/10.1016/j.jag.2023.103406 |x Verlag |x Resolving-System |z lizenzpflichtig |3 Volltext |
| 856 | 4 | 0 | |u https://www.sciencedirect.com/science/article/pii/S1569843223002303 |x Verlag |z lizenzpflichtig |3 Volltext |
| 951 | |a AR | ||
| 992 | |a 20230720 | ||
| 993 | |a Article | ||
| 994 | |a 2023 | ||
| 998 | |g 1019895403 |a Höfle, Bernhard |m 1019895403:Höfle, Bernhard |d 120000 |d 120700 |d 700000 |d 729400 |e 120000PH1019895403 |e 120700PH1019895403 |e 700000PH1019895403 |e 729400PH1019895403 |k 0/120000/ |k 1/120000/120700/ |k 0/700000/ |k 1/700000/729400/ |p 5 |y j | ||
| 998 | |g 1128842580 |a Anders, Katharina |m 1128842580:Anders, Katharina |d 120000 |d 120700 |e 120000PA1128842580 |e 120700PA1128842580 |k 0/120000/ |k 1/120000/120700/ |p 2 | ||
| 998 | |g 1227935412 |a Zahs, Vivien |m 1227935412:Zahs, Vivien |d 120000 |d 120700 |e 120000PZ1227935412 |e 120700PZ1227935412 |k 0/120000/ |k 1/120000/120700/ |p 1 |x j | ||
| 999 | |a KXP-PPN1853179108 |e 4355516415 | ||
| BIB | |a Y | ||
| SER | |a journal | ||
| JSO | |a {"note":["Online verfügbar: 15. Juli 2023, Artikelversion: 15. Juli 2023","Gesehen am 20.07.2023"],"recId":"1853179108","name":{"displayForm":["Vivien Zahs, Katharina Anders, Julia Kohns, Alexander Stark, Bernhard Höfle"]},"type":{"bibl":"article-journal","media":"Online-Ressource"},"id":{"doi":["10.1016/j.jag.2023.103406"],"eki":["1853179108"]},"language":["eng"],"origin":[{"dateIssuedKey":"2023","dateIssuedDisp":"August 2023"}],"relHost":[{"disp":"Classification of structural building damage grades from multi-temporal photogrammetric point clouds using a machine learning model trained on virtual laser scanning dataInternational journal of applied earth observation and geoinformation","recId":"359784119","pubHistory":["1.1999 - 13.2011; Vol. 14.2012 -"],"note":["Gesehen am 20.02.2023"],"type":{"media":"Online-Ressource","bibl":"periodical"},"id":{"issn":["1872-826X"],"zdb":["2097960-5"],"eki":["359784119"]},"language":["eng"],"origin":[{"dateIssuedKey":"1999","publisher":"Elsevier Science","dateIssuedDisp":"1999-","publisherPlace":"Amsterdam [u.a.]"}],"title":[{"title":"International journal of applied earth observation and geoinformation","title_sort":"International journal of applied earth observation and geoinformation"}],"physDesc":[{"extent":"Online-Ressource"}],"part":{"pages":"1-15","text":"122(2023) vom: Aug., Artikel-ID 103406, Seite 1-15","volume":"122","year":"2023","extent":"15"}}],"person":[{"role":"aut","given":"Vivien","family":"Zahs","display":"Zahs, Vivien"},{"given":"Katharina","display":"Anders, Katharina","family":"Anders","role":"aut"},{"role":"aut","display":"Kohns, Julia","family":"Kohns","given":"Julia"},{"family":"Stark","display":"Stark, Alexander","given":"Alexander","role":"aut"},{"role":"aut","family":"Höfle","display":"Höfle, Bernhard","given":"Bernhard"}],"physDesc":[{"noteIll":"Illustrationen","extent":"15 S."}],"title":[{"title_sort":"Classification of structural building damage grades from multi-temporal photogrammetric point clouds using a machine learning model trained on virtual laser scanning data","title":"Classification of structural building damage grades from multi-temporal photogrammetric point clouds using a machine learning model trained on virtual laser scanning data"}]} | ||
| SRT | |a ZAHSVIVIENCLASSIFICA2023 | ||