elib
DLR-Header
DLR-Logo -> http://www.dlr.de
DLR Portal Home | Impressum | Datenschutz | Kontakt | English
Schriftgröße: [-] Text [+]

Rule-Based, Noisy Labels for Overhead Imagery Segmentation

Albrecht, Conrad M und Liu, Chenying und Wang, Yi und Klein, Levente J und Zhu, Xiao Xiang (2022) Rule-Based, Noisy Labels for Overhead Imagery Segmentation. Living Planet Symposium, 2022-05-23 - 2022-05-27, Bonn, Germany.

[img] PDF
1MB

Kurzfassung

Within the past decade, modern statistical and machine learning methods significantly advanced the field of computer vision. For a significant portion, success stories trace back to training deep artificial neural networks on massive amounts of labeled data. However, generating human labor-intensive annotations for the ever-growing volume of earth observation data at scale renders Sysiphus-like. In the realm of weakly-supervised learning, methods operating on sparse labels attempt to exploit a small set of annotated data in order to train models for inference on the full domain of input. Our work presents a methodology to utilize high resolution geospatial data for semantic segmentation of aerial imagery. Specifically, we exploit high-quality LiDAR measurements to automatically generate a set of labels for urban areas based on rules defined by domain experts. The top of the figure attached provides a visual sample for such automatized classifications in suburbs: vegetation (dark madder purple), roads (lime green), buildings (dark green), and bare land (yellow). A challenge to the approach of auto-generated labels is introduction of noise due to inaccurate label information. Through benchmarks and improved architecture design of the deep artificial neural networks, we provide insights on success and limitations of our approach. Remarkably, we demonstrate that models trained on inaccurate labels have the ability to surpass annotation quality when referenced to ground truth information (cf. bottom of figure attached). Moreover, we investigate boosting of results when weak labels get auto-corrected by domain expert-based noise reduction algorithms. We propose technology interacting with deep neural network architectures that allows human expertise to re-enter weakly supervised learning at scale for semantic segmentation in earth observation. Beyond the presentation of results, our contribution @LPS22 intends to start a vital scientific discussion on how the approach substantiated for LiDAR-based automatic annotation might get extended to other modalities such as hyper-spectral overhead imagery.

elib-URL des Eintrags:https://elib.dlr.de/186653/
Dokumentart:Konferenzbeitrag (Poster)
Titel:Rule-Based, Noisy Labels for Overhead Imagery Segmentation
Autoren:
AutorenInstitution oder E-Mail-AdresseAutoren-ORCID-iDORCID Put Code
Albrecht, Conrad MConrad.Albrecht (at) dlr.dehttps://orcid.org/0009-0009-2422-7289NICHT SPEZIFIZIERT
Liu, Chenyingchenying.liu (at) dlr.dehttps://orcid.org/0000-0001-9172-3586NICHT SPEZIFIZIERT
Wang, YiYi.Wang (at) dlr.deNICHT SPEZIFIZIERTNICHT SPEZIFIZIERT
Klein, Levente Jkleinl (at) us.ibm.comNICHT SPEZIFIZIERTNICHT SPEZIFIZIERT
Zhu, Xiao Xiangxiao.zhu (at) dlr.deNICHT SPEZIFIZIERTNICHT SPEZIFIZIERT
Datum:Mai 2022
Referierte Publikation:Nein
Open Access:Ja
Gold Open Access:Nein
In SCOPUS:Nein
In ISI Web of Science:Nein
Status:veröffentlicht
Stichwörter:LiDAR, deep learning, semantic segmentation, weak supervision, noisy labels
Veranstaltungstitel:Living Planet Symposium
Veranstaltungsort:Bonn, Germany
Veranstaltungsart:internationale Konferenz
Veranstaltungsbeginn:23 Mai 2022
Veranstaltungsende:27 Mai 2022
Veranstalter :European Space Agency
HGF - Forschungsbereich:Luftfahrt, Raumfahrt und Verkehr
HGF - Programm:Raumfahrt
HGF - Programmthema:Erdbeobachtung
DLR - Schwerpunkt:Raumfahrt
DLR - Forschungsgebiet:R EO - Erdbeobachtung
DLR - Teilgebiet (Projekt, Vorhaben):R - Künstliche Intelligenz
Standort: Oberpfaffenhofen
Institute & Einrichtungen:Institut für Methodik der Fernerkundung > EO Data Science
Hinterlegt von: Albrecht, Conrad M
Hinterlegt am:03 Jun 2022 10:52
Letzte Änderung:24 Apr 2024 20:48

Nur für Mitarbeiter des Archivs: Kontrollseite des Eintrags

Blättern
Suchen
Hilfe & Kontakt
Informationen
electronic library verwendet EPrints 3.3.12
Gestaltung Webseite und Datenbank: Copyright © Deutsches Zentrum für Luft- und Raumfahrt (DLR). Alle Rechte vorbehalten.