elib
DLR-Header
DLR-Logo -> http://www.dlr.de
DLR Portal Home | Imprint | Privacy Policy | Contact | Deutsch
Fontsize: [-] Text [+]

AutoGeoLabel: Automated Label Generation for Geospatial Machine Learning

Albrecht, Conrad M. and Marianno, Fernando and Klein, Levente J (2021) AutoGeoLabel: Automated Label Generation for Geospatial Machine Learning. In: 2021 IEEE International Conference on Big Data (Big Data), pp. 1779-1786. 2021 IEEE International Conference on Big Data (Big Data), virtual. doi: 10.1109/BigData52589.2021.9672060.

[img] PDF - Only accessible within DLR bis February 2023
7MB

Official URL: https://ieeexplore.ieee.org/document/9672060

Abstract

Abstract—A key challenge of supervised learning is the availability of human-labeled data. We evaluate a big data processing pipeline to auto-generate labels for remote sensing data. It is based on rasterized statistical features extracted from surveys such as e.g. LiDAR measurements. Using simple combinations of the rasterized statistical layers, it is demonstrated that multiple classes can be generated at accuracies of ∼0.9. As proof of concept, we utilize the big geo-data platform IBM PAIRS to dynamically generate such labels in dense urban areas with multiple land cover classes. The general method proposed here is platform independent, and it can be adapted to generate labels for other satellite modalities in order to enable machine learning on overhead imagery for land use classification and object detection.

Item URL in elib:https://elib.dlr.de/148608/
Document Type:Conference or Workshop Item (Speech)
Title:AutoGeoLabel: Automated Label Generation for Geospatial Machine Learning
Authors:
AuthorsInstitution or Email of AuthorsAuthor's ORCID iD
Albrecht, Conrad M.Conrad.Albrecht (at) dlr.deUNSPECIFIED
Marianno, Fernandofjmarian (at) us.ibm.comUNSPECIFIED
Klein, Levente Jkleinl (at) us.ibm.comUNSPECIFIED
Date:December 2021
Journal or Publication Title:2021 IEEE International Conference on Big Data (Big Data)
Refereed publication:Yes
Open Access:No
Gold Open Access:No
In SCOPUS:No
In ISI Web of Science:No
DOI :10.1109/BigData52589.2021.9672060
Page Range:pp. 1779-1786
Status:Published
Keywords:Geospatial analysis, Laser radar, Big data applications, Weak supervision
Event Title:2021 IEEE International Conference on Big Data (Big Data)
Event Location:virtual
Event Type:international Conference
Organizer:IEEE
HGF - Research field:other
HGF - Program:other
HGF - Program Themes:other
DLR - Research area:Digitalisation
DLR - Program:D CPE - Cyberphysical Engineering
DLR - Research theme (Project):D - urbanModel
Location: Oberpfaffenhofen
Institutes and Institutions:Remote Sensing Technology Institute > EO Data Science
Deposited By: Albrecht, Conrad M
Deposited On:03 Feb 2022 10:18
Last Modified:04 Feb 2022 09:58

Repository Staff Only: item control page

Browse
Search
Help & Contact
Information
electronic library is running on EPrints 3.3.12
Copyright © 2008-2017 German Aerospace Center (DLR). All rights reserved.