Konferenzveröffentlichung
Enhancing Wind Turbine Location Accuracy: a Deep Learning-Based Object Regression Approach for Validating Wind Turbine Geo-Coordinates
Abstract
Remote sensing and deep learning-based methods can be combined to obtain location information automatically on a large scale. This paper introduces an approach for enhancing the geo-coordinate accuracy of existing wind turbines. By employing a RetinaNet-based method for regressive object localization, turbines can be precisely located in images in addition to being identified. Utilizing semi-automatically processed and manually filtered high-resolution image data, a model is trained with an average precision of 96 %. Subsequently, the model is applied to Germany’s MaStR wind turbine dataset. The application illustrates the advantageous implementation of the method and emphasizes its considerable potential for improving the accuracy of geo-coordinates. While 73.72 % of existing coordinates can be confirmed as correct with a deviation of less than 10 meter, for more than 15 % of the turbine locations coordinates between 10 and 100 meters can be corrected, and for 5.6 % locations a deviation of more than 100 meter can be determined. This showcases the real-world application of the proposed methodology and underscores its significant potential for enhancing the quality of geo-coordinates.
Additional Information
Autorenversion; © 2024 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.Citation
@inproceedings{doi:10.17170/kobra-2024102410992,
author={Kleebauer, Maximilian and Braun, Axel and Horst, Daniel and Pape, Carsten},
title={Enhancing Wind Turbine Location Accuracy: a Deep Learning-Based Object Regression Approach for Validating Wind Turbine Geo-Coordinates},
booktitle={IGARSS 2024 - 2024 IEEE International Geoscience and Remote Sensing Symposium. Proceedings},
year={2024}
}
0500 Oax
0501 Text $btxt$2rdacontent
0502 Computermedien $bc$2rdacarrier
1100 2024$n2024
1500 1/eng
2050 ##0##http://hdl.handle.net/123456789/16112
3000 Kleebauer, Maximilian
3010 Braun, Axel
3010 Horst, Daniel
3010 Pape, Carsten
4000 Enhancing Wind Turbine Location Accuracy: a Deep Learning-Based Object Regression Approach for Validating Wind Turbine Geo-Coordinates / Kleebauer, Maximilian
4030
4060 Online-Ressource
4085 ##0##=u http://nbn-resolving.de/http://hdl.handle.net/123456789/16112=x R
4204 \$dKonferenzveröffentlichung
4170
5550 {{Windturbine}}
5550 {{Erneuerbare Energien}}
5550 {{Geoinformation}}
5550 {{Deep learning}}
5550 {{Fernerkundung}}
7136 ##0##http://hdl.handle.net/123456789/16112
<resource xsi:schemaLocation="http://datacite.org/schema/kernel-2.2 http://schema.datacite.org/meta/kernel-2.2/metadata.xsd"> 2024-10-25T08:24:33Z 2024-10-25T08:24:33Z 2024 doi:10.17170/kobra-2024102410992 http://hdl.handle.net/123456789/16112 Autorenversion; © 2024 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. eng IEEE Urheberrechtlich geschützt https://rightsstatements.org/page/InC/1.0/ wind turbines renewable energy systems object regression geo-coordinate validation 600 Enhancing Wind Turbine Location Accuracy: a Deep Learning-Based Object Regression Approach for Validating Wind Turbine Geo-Coordinates Konferenzveröffentlichung Remote sensing and deep learning-based methods can be combined to obtain location information automatically on a large scale. This paper introduces an approach for enhancing the geo-coordinate accuracy of existing wind turbines. By employing a RetinaNet-based method for regressive object localization, turbines can be precisely located in images in addition to being identified. Utilizing semi-automatically processed and manually filtered high-resolution image data, a model is trained with an average precision of 96 %. Subsequently, the model is applied to Germany’s MaStR wind turbine dataset. The application illustrates the advantageous implementation of the method and emphasizes its considerable potential for improving the accuracy of geo-coordinates. While 73.72 % of existing coordinates can be confirmed as correct with a deviation of less than 10 meter, for more than 15 % of the turbine locations coordinates between 10 and 100 meters can be corrected, and for 5.6 % locations a deviation of more than 100 meter can be determined. This showcases the real-world application of the proposed methodology and underscores its significant potential for enhancing the quality of geo-coordinates. open access Kleebauer, Maximilian Braun, Axel Horst, Daniel Pape, Carsten doi:10.1109/IGARSS53475.2024.10641018 Windturbine Erneuerbare Energien Geoinformation Deep learning Fernerkundung acceptedVersion 2024-07-07 Athen IGARSS 2024 - 2024 IEEE International Geoscience and Remote Sensing Symposium. Proceedings eisbn: 979-8-3503-6032-5 isbn:979-8-3503-6033-2 doi:10.1109/IGARSS53475.2024 7863-7867 false IGARSS 2024 - 2024 IEEE International Geoscience and Remote Sensing Symposium </resource>
The following license files are associated with this item:
:Urheberrechtlich geschützt