Show simple item record

dc.contributor.authorMboga, N.
dc.contributor.authorD Aronco, S.
dc.contributor.authorGrippa, T.
dc.contributor.authorPelletier, C.
dc.contributor.authorGeorganos, S.
dc.contributor.authorVanhuysse, S.
dc.contributor.authorWolff, E.
dc.contributor.authorSmets, B.
dc.contributor.authorDewitte, O.
dc.date2021
dc.date.accessioned2024-03-14T13:25:31Z
dc.date.available2024-03-14T13:25:31Z
dc.identifier.urihttps://orfeo.belnet.be/handle/internal/12732
dc.descriptionMultitemporal environmental and urban studies are essential to guide policy making to ultimately improve human wellbeing in the Global South. Land-cover products derived from historical aerial orthomosaics acquired decades ago can provide important evidence to inform long-term studies. To reduce the manual labelling effort by human experts and to scale to large, meaningful regions, we investigate in this study how domain adaptation techniques and deep learning can help to efficiently map land cover in Central Africa. We propose and evaluate a methodology that is based on unsupervised adaptation to reduce the cost of generating reference data for several cities and across different dates. We present the first application of domain adaptation based on fully convolutional networks for semantic segmentation of a dataset of historical panchromatic orthomosaics for land-cover generation for two focus cities Goma-Gisenyi and Bukavu. Our experimental evaluation shows that the domain adaptation methods can reach an overall accuracy between 60% and 70% for different regions. If we add a small amount of labelled data from the target domain, too, further performance gains can be achieved.
dc.languageeng
dc.titleDomain adaptation for semantic segmentation of historical panchromatic orthomosaics in Central Africa
dc.typeArticle
dc.subject.frascatiComputer and information sciences
dc.audienceScientific
dc.subject.freeNatural hazards
dc.source.titleISPRS International Journal of Geo-Information
dc.source.volume10
dc.source.page523
Orfeo.peerreviewedYes
dc.identifier.doihttps://doi.org/10.3390/ijgi10080523
dc.identifier.rmca6180


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record