Improving Road Surface Area Extraction via Semantic Segmentation with Conditional Generative Learning for Deep Inpainting Operations

dc.contributor.authorCira, Calimanut-Ionut
dc.contributor.authorKada, Martin
dc.contributor.authorManso-Callejo, Miguel-Ángel
dc.contributor.authorAlcarria, Ramón
dc.contributor.authorBordel Sanchez, Borja
dc.date.accessioned2022-02-14T14:03:10Z
dc.date.available2022-02-14T14:03:10Z
dc.date.issued2022-01-09
dc.date.updated2022-02-08T18:18:12Z
dc.description.abstractThe road surface area extraction task is generally carried out via semantic segmentation over remotely-sensed imagery. However, this supervised learning task is often costly as it requires remote sensing images labelled at the pixel level, and the results are not always satisfactory (presence of discontinuities, overlooked connection points, or isolated road segments). On the other hand, unsupervised learning does not require labelled data and can be employed for post-processing the geometries of geospatial objects extracted via semantic segmentation. In this work, we implement a conditional Generative Adversarial Network to reconstruct road geometries via deep inpainting procedures on a new dataset containing unlabelled road samples from challenging areas present in official cartographic support from Spain. The goal is to improve the initial road representations obtained with semantic segmentation models via generative learning. The performance of the model was evaluated on unseen data by conducting a metrical comparison where a maximum Intersection over Union (IoU) score improvement of 1.3% was observed when compared to the initial semantic segmentation result. Next, we evaluated the appropriateness of applying unsupervised generative learning using a qualitative perceptual validation to identify the strengths and weaknesses of the proposed method in very complex scenarios and gain a better intuition of the model’s behaviour when performing large-scale post-processing with generative learning and deep inpainting procedures and observed important improvements in the generated data.en
dc.identifier.eissn2220-9964
dc.identifier.urihttps://depositonce.tu-berlin.de/handle/11303/16361
dc.identifier.urihttp://dx.doi.org/10.14279/depositonce-15137
dc.language.isoenen
dc.rightsLicensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/en
dc.subject.ddc550 Geowissenschaftende
dc.subject.otherconditional learningen
dc.subject.othergenerative adversarial networken
dc.subject.othergenerative learningen
dc.subject.otherimage inpaintingen
dc.subject.otherimage post-processingen
dc.subject.otherroad extractionen
dc.subject.otherunsupervised learningen
dc.titleImproving Road Surface Area Extraction via Semantic Segmentation with Conditional Generative Learning for Deep Inpainting Operationsen
dc.typeArticleen
dc.type.versionpublishedVersionen
dcterms.bibliographicCitation.articlenumber43en
dcterms.bibliographicCitation.doi10.3390/ijgi11010043en
dcterms.bibliographicCitation.issue1en
dcterms.bibliographicCitation.journaltitleISPRS International Journal of Geo-Informationen
dcterms.bibliographicCitation.originalpublishernameMDPIen
dcterms.bibliographicCitation.originalpublisherplaceBaselen
dcterms.bibliographicCitation.volume11en
tub.accessrights.dnbfreeen
tub.affiliationFak. 6 Planen Bauen Umwelt>Inst. Geodäsie und Geoinformationstechnik>FG Methodik der Geoinformationstechnikde
tub.affiliation.facultyFak. 6 Planen Bauen Umweltde
tub.affiliation.groupFG Methodik der Geoinformationstechnikde
tub.affiliation.instituteInst. Geodäsie und Geoinformationstechnikde
tub.publisher.universityorinstitutionTechnische Universität Berlinen
Files
Original bundle
Now showing 1 - 1 of 1
Loading…
Thumbnail Image
Name:
ijgi-11-00043-v3.pdf
Size:
2.35 MB
Format:
Adobe Portable Document Format
Description:
Collections