ON THE SEMANTIC SEGMENTATION AND VALIDATION OF ELECTRICAL SUBSTATIONS
Abstract. Converting deep learning methods from benchmark testing to real applications is highly sought after both in academia and the industry. Key challenges that remain are the performance of the methods on new datasets, the preprocessing of the data and the integration of the results into application pipelines. Specifically for the implementation of semantic segmentation procedures, each of these challenges are still very much the subject of research. In this paper, we present a testcase to digitally twin and validate an electrical substation. Concretely, we discuss the data processing, training and the follow up integration of the results in the validation pipeline. In the experiments, we show that 86% initial F1-score can be achieved using the proper transfer learning on 14 classes and that this results in a 97% recall on the validation and 80% recall on the digitization of the substation. Overall, we show that the segmentation significantly contributes to these processes and that they are absolutely necessary for the automation of the digital twinning.
- Location
-
Deutsche Nationalbibliothek Frankfurt am Main
- Extent
-
Online-Ressource
- Language
-
Englisch
- Bibliographic citation
-
ON THE SEMANTIC SEGMENTATION AND VALIDATION OF ELECTRICAL SUBSTATIONS ; volume:XLVIII-1/W2-2023 ; year:2023 ; pages:131-138 ; extent:8
The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences ; XLVIII-1/W2-2023 (2023), 131-138 (gesamt 8)
- Creator
-
Bassier, M.
- DOI
-
10.5194/isprs-archives-XLVIII-1-W2-2023-131-2023
- URN
-
urn:nbn:de:101:1-2023121403152299098207
- Rights
-
Open Access; Der Zugriff auf das Objekt ist unbeschränkt möglich.
- Last update
-
15.08.2025, 7:30 AM CEST
Data provider
Deutsche Nationalbibliothek. If you have any questions about the object, please contact the data provider.
Associated
- Bassier, M.
Other Objects (12)
Active semantic segmentation on a time budget
Cross-validation of a semantic segmentation network for natural history collection specimens
Semantic Segmentation of Ambiguous Images
Semantic segmentation of textured mosaics
Sfnet: Faster and Accurate Semantic Segmentation Via Semantic Flow
Extrinsic Camera Calibration with Semantic Segmentation
Robust Semantic Segmentation with Deep Learning
Recent progress in semantic image segmentation
Detecting Anything Overlooked in Semantic Segmentation
SigUNet: signal peptide recognition based on semantic segmentation
Supporting Explainable AI on Semantic Constraint Validation
CT image segmentation of foxtail millet seeds based on semantic segmentation model VGG16-UNet
Active semantic segmentation on a time budget
Cross-validation of a semantic segmentation network for natural history collection specimens
Semantic Segmentation of Ambiguous Images
Semantic segmentation of textured mosaics
Sfnet: Faster and Accurate Semantic Segmentation Via Semantic Flow
Extrinsic Camera Calibration with Semantic Segmentation
Robust Semantic Segmentation with Deep Learning
Recent progress in semantic image segmentation
Detecting Anything Overlooked in Semantic Segmentation
SigUNet: signal peptide recognition based on semantic segmentation
Supporting Explainable AI on Semantic Constraint Validation
CT image segmentation of foxtail millet seeds based on semantic segmentation model VGG16-UNet
Active semantic segmentation on a time budget
Cross-validation of a semantic segmentation network for natural history collection specimens
Semantic Segmentation of Ambiguous Images
Semantic segmentation of textured mosaics
Sfnet: Faster and Accurate Semantic Segmentation Via Semantic Flow
Extrinsic Camera Calibration with Semantic Segmentation
Robust Semantic Segmentation with Deep Learning
Recent progress in semantic image segmentation
Detecting Anything Overlooked in Semantic Segmentation
SigUNet: signal peptide recognition based on semantic segmentation
Supporting Explainable AI on Semantic Constraint Validation