Improving OpenStreetMap missing building detection using few-shot transfer learning in sub-Saharan Africa

OpenStreetMap (OSM) has been intensively used to support humanitarian aid activities, especially in the Global South. Its data availability in the Global South has been greatly improved via recent humanitarian mapping campaigns. However, large rural areas are still incompletely mapped. The timely pr...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Li, Hao (VerfasserIn) , Herfort, Benjamin (VerfasserIn) , Lautenbach, Sven (VerfasserIn) , Chen, Jiaoyan (VerfasserIn) , Zipf, Alexander (VerfasserIn)
Dokumenttyp: Article (Journal)
Sprache:Englisch
Veröffentlicht: December 2022
In: Transactions in GIS
Year: 2022, Jahrgang: 26, Heft: 8, Pages: 3125-3146
ISSN:1467-9671
DOI:10.1111/tgis.12941
Online-Zugang:Verlag, kostenfrei, Volltext: https://doi.org/10.1111/tgis.12941
Verlag, kostenfrei, Volltext: https://onlinelibrary.wiley.com/doi/abs/10.1111/tgis.12941
Volltext
Verfasserangaben:Hao Li, Benjamin Herfort, Sven Lautenbach, Jiaoyan Chen, Alexander Zipf

MARC

LEADER 00000naa a2200000 c 4500
001 1941186084
003 DE-627
005 20251113160310.0
007 cr uuu---uuuuu
008 251113s2022 xx |||||o 00| ||eng c
024 7 |a 10.1111/tgis.12941  |2 doi 
035 |a (DE-627)1941186084 
035 |a (DE-599)KXP1941186084 
040 |a DE-627  |b ger  |c DE-627  |e rda 
041 |a eng 
084 |a 61  |2 sdnb 
100 1 |a Li, Hao  |e VerfasserIn  |0 (DE-588)1197649670  |0 (DE-627)1679340883  |4 aut 
245 1 0 |a Improving OpenStreetMap missing building detection using few-shot transfer learning in sub-Saharan Africa  |c Hao Li, Benjamin Herfort, Sven Lautenbach, Jiaoyan Chen, Alexander Zipf 
264 1 |c December 2022 
300 |a 22 
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 veröffentlicht: 4. Mai 2022 
500 |a Gesehen am 13.11.2025 
520 |a OpenStreetMap (OSM) has been intensively used to support humanitarian aid activities, especially in the Global South. Its data availability in the Global South has been greatly improved via recent humanitarian mapping campaigns. However, large rural areas are still incompletely mapped. The timely provision of map data is often essential for the work of humanitarian actors in the case of disaster preparation or disaster response. Therefore, it has become a vital challenge to boost the speed and efficiency of existing humanitarian mapping workflows. We address this challenge by proposing a novel few-shot transfer learning (FSTL) method to improve the accuracy of OSM missing building detection. We trained two popular object detection models (i.e., Faster R-CNN and SSD) in a training area in Tanzania and transferred the model to target areas in Cameroon and Mozambique. The FSTL method significantly improved the base model performance even with only one training shot. Moreover, we successfully produced a grid-based OSM missing building map (DeepVGI) of 10 m spatial resolution with over 96% overall accuracy (ACC) and 0.85 Matthews correlation coefficient (MCC) in both Cameroon and Mozambique. Such maps show great potential to assess and estimate the overall completeness of OSM buildings to support humanitarian mapping activities, especially in places where other (e.g., buildings, roads) datasets are not available. 
700 1 |a Herfort, Benjamin  |d 1991-  |e VerfasserIn  |0 (DE-588)1066402140  |0 (DE-627)817493832  |0 (DE-576)425832473  |4 aut 
700 1 |a Lautenbach, Sven  |d 1969-  |e VerfasserIn  |0 (DE-588)131532847  |0 (DE-627)510504264  |0 (DE-576)29856811X  |4 aut 
700 1 |a Chen, Jiaoyan  |e VerfasserIn  |0 (DE-588)1187539295  |0 (DE-627)1666566799  |4 aut 
700 1 |a Zipf, Alexander  |d 1971-  |e VerfasserIn  |0 (DE-588)123246369  |0 (DE-627)082437076  |0 (DE-576)175641056  |4 aut 
773 0 8 |i Enthalten in  |t Transactions in GIS  |d Oxford : Wiley-Blackwell, 1996  |g 26(2022), 8 vom: Dez., Seite 3125-3146  |h Online-Ressource  |w (DE-627)325295948  |w (DE-600)2035222-0  |w (DE-576)11519777X  |x 1467-9671  |7 nnas  |a Improving OpenStreetMap missing building detection using few-shot transfer learning in sub-Saharan Africa 
773 1 8 |g volume:26  |g year:2022  |g number:8  |g month:12  |g pages:3125-3146  |g extent:22  |a Improving OpenStreetMap missing building detection using few-shot transfer learning in sub-Saharan Africa 
856 4 0 |u https://doi.org/10.1111/tgis.12941  |x Verlag  |x Resolving-System  |z kostenfrei  |3 Volltext 
856 4 0 |u https://onlinelibrary.wiley.com/doi/abs/10.1111/tgis.12941  |x Verlag  |z kostenfrei  |3 Volltext 
951 |a AR 
992 |a 20251113 
993 |a Article 
994 |a 2022 
998 |g 123246369  |a Zipf, Alexander  |m 123246369:Zipf, Alexander  |d 120000  |d 120700  |e 120000PZ123246369  |e 120700PZ123246369  |k 0/120000/  |k 1/120000/120700/  |p 5  |y j 
998 |g 131532847  |a Lautenbach, Sven  |m 131532847:Lautenbach, Sven  |d 120000  |d 120000  |d 120700  |e 120000PL131532847  |e 120000PL131532847  |e 120700PL131532847  |k 0/120000/  |k 0/120000/  |k 1/120000/120700/  |p 3 
998 |g 1066402140  |a Herfort, Benjamin  |m 1066402140:Herfort, Benjamin  |d 120000  |d 120700  |e 120000PH1066402140  |e 120700PH1066402140  |k 0/120000/  |k 1/120000/120700/  |p 2 
998 |g 1197649670  |a Li, Hao  |m 1197649670:Li, Hao  |d 120000  |d 120700  |e 120000PL1197649670  |e 120700PL1197649670  |k 0/120000/  |k 1/120000/120700/  |p 1  |x j 
999 |a KXP-PPN1941186084  |e 4804502785 
BIB |a Y 
SER |a journal 
JSO |a {"physDesc":[{"extent":"22 S."}],"id":{"doi":["10.1111/tgis.12941"],"eki":["1941186084"]},"type":{"media":"Online-Ressource","bibl":"article-journal"},"title":[{"title":"Improving OpenStreetMap missing building detection using few-shot transfer learning in sub-Saharan Africa","title_sort":"Improving OpenStreetMap missing building detection using few-shot transfer learning in sub-Saharan Africa"}],"origin":[{"dateIssuedDisp":"December 2022","dateIssuedKey":"2022"}],"relHost":[{"pubHistory":["Volume 1, Issue 1 (January 1996)-"],"note":["Gesehen am 26.04.2018"],"part":{"volume":"26","year":"2022","issue":"8","extent":"22","pages":"3125-3146","text":"26(2022), 8 vom: Dez., Seite 3125-3146"},"language":["eng"],"disp":"Improving OpenStreetMap missing building detection using few-shot transfer learning in sub-Saharan AfricaTransactions in GIS","type":{"bibl":"periodical","media":"Online-Ressource"},"recId":"325295948","origin":[{"publisherPlace":"Oxford ; Cambridge","dateIssuedKey":"1996","dateIssuedDisp":"1996-","publisher":"Wiley-Blackwell ; Blackwell Publ."}],"physDesc":[{"extent":"Online-Ressource"}],"id":{"issn":["1467-9671"],"eki":["325295948"],"zdb":["2035222-0"],"doi":["10.1111/(ISSN)1467-9671"]},"title":[{"title_sort":"Transactions in GIS","title":"Transactions in GIS"}]}],"language":["eng"],"name":{"displayForm":["Hao Li, Benjamin Herfort, Sven Lautenbach, Jiaoyan Chen, Alexander Zipf"]},"note":["Online veröffentlicht: 4. Mai 2022","Gesehen am 13.11.2025"],"recId":"1941186084","person":[{"given":"Hao","display":"Li, Hao","role":"aut","family":"Li"},{"given":"Benjamin","display":"Herfort, Benjamin","family":"Herfort","role":"aut"},{"given":"Sven","display":"Lautenbach, Sven","role":"aut","family":"Lautenbach"},{"role":"aut","family":"Chen","display":"Chen, Jiaoyan","given":"Jiaoyan"},{"role":"aut","family":"Zipf","display":"Zipf, Alexander","given":"Alexander"}]} 
SRT |a LIHAOHERFOIMPROVINGO2022