Fully Automated Segmentation of 2D and 3D Mobile Mapping Data for Reliable Modeling of Surface Structures Using Deep Learning
Maintenance and expansion of transport and communications infrastructure requires ongoing construction work on a large scale. To plan and execute these in the best possible way, up-to-date and highly detailed digital maps are needed. For example, until recently, telecommunication companies have perf...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-08-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/12/16/2530 |
| _version_ | 1797559950876082176 |
|---|---|
| author | Alexander Reiterer Katharina Wäschle Dominik Störk Achim Leydecker Niko Gitzen |
| author_facet | Alexander Reiterer Katharina Wäschle Dominik Störk Achim Leydecker Niko Gitzen |
| author_sort | Alexander Reiterer |
| collection | DOAJ |
| description | Maintenance and expansion of transport and communications infrastructure requires ongoing construction work on a large scale. To plan and execute these in the best possible way, up-to-date and highly detailed digital maps are needed. For example, until recently, telecommunication companies have performed documentation and mapping of as-built urban structures for construction work manually and with great time expense. Mobile mapping systems offer a solution for documenting urban environments fast and mostly automated. In consequence, large amounts of recorded data emerge in short time, creating the need for automated processing and modeling of these data to provide reliable foundations for digital planning in reasonable time. We present (a) a procedure for fully automated processing of mobile mapping data for digital construction planning in the context of nationwide broadband network expansion and (b) an in-depth study of the performance of this procedure on real-world data. Our multi-stage pipeline segments georeferenced images and fuses segmentations with 3D data, which allows exact localization of surfaces and objects, which can then be passed via interface, e.g., to a geographic information system (GIS). The final system is able to distinguish between similar looking surfaces, such as concrete and asphalt, with a precision between 80% and 95%, regardless of setting or season. |
| first_indexed | 2024-03-10T17:52:29Z |
| format | Article |
| id | doaj.art-14ba73a4c34844d4a4c2080b49347f5e |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-10T17:52:29Z |
| publishDate | 2020-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-14ba73a4c34844d4a4c2080b49347f5e2023-11-20T09:17:26ZengMDPI AGRemote Sensing2072-42922020-08-011216253010.3390/rs12162530Fully Automated Segmentation of 2D and 3D Mobile Mapping Data for Reliable Modeling of Surface Structures Using Deep LearningAlexander Reiterer0Katharina Wäschle1Dominik Störk2Achim Leydecker3Niko Gitzen4Fraunhofer Institute for Physical Measurement Techniques IPM, 79110 Freiburg, GermanyFraunhofer Institute for Physical Measurement Techniques IPM, 79110 Freiburg, GermanyFraunhofer Institute for Physical Measurement Techniques IPM, 79110 Freiburg, GermanyFraunhofer Institute for Physical Measurement Techniques IPM, 79110 Freiburg, GermanyFTTH Factory Produktion, Deutsche Telekom Technik GmbH, 53227 Bonn, GermanyMaintenance and expansion of transport and communications infrastructure requires ongoing construction work on a large scale. To plan and execute these in the best possible way, up-to-date and highly detailed digital maps are needed. For example, until recently, telecommunication companies have performed documentation and mapping of as-built urban structures for construction work manually and with great time expense. Mobile mapping systems offer a solution for documenting urban environments fast and mostly automated. In consequence, large amounts of recorded data emerge in short time, creating the need for automated processing and modeling of these data to provide reliable foundations for digital planning in reasonable time. We present (a) a procedure for fully automated processing of mobile mapping data for digital construction planning in the context of nationwide broadband network expansion and (b) an in-depth study of the performance of this procedure on real-world data. Our multi-stage pipeline segments georeferenced images and fuses segmentations with 3D data, which allows exact localization of surfaces and objects, which can then be passed via interface, e.g., to a geographic information system (GIS). The final system is able to distinguish between similar looking surfaces, such as concrete and asphalt, with a precision between 80% and 95%, regardless of setting or season.https://www.mdpi.com/2072-4292/12/16/2530mobile mapping systemsroad surface texturesupervised learningsemantic segmentationbroadband infrastructure |
| spellingShingle | Alexander Reiterer Katharina Wäschle Dominik Störk Achim Leydecker Niko Gitzen Fully Automated Segmentation of 2D and 3D Mobile Mapping Data for Reliable Modeling of Surface Structures Using Deep Learning Remote Sensing mobile mapping systems road surface texture supervised learning semantic segmentation broadband infrastructure |
| title | Fully Automated Segmentation of 2D and 3D Mobile Mapping Data for Reliable Modeling of Surface Structures Using Deep Learning |
| title_full | Fully Automated Segmentation of 2D and 3D Mobile Mapping Data for Reliable Modeling of Surface Structures Using Deep Learning |
| title_fullStr | Fully Automated Segmentation of 2D and 3D Mobile Mapping Data for Reliable Modeling of Surface Structures Using Deep Learning |
| title_full_unstemmed | Fully Automated Segmentation of 2D and 3D Mobile Mapping Data for Reliable Modeling of Surface Structures Using Deep Learning |
| title_short | Fully Automated Segmentation of 2D and 3D Mobile Mapping Data for Reliable Modeling of Surface Structures Using Deep Learning |
| title_sort | fully automated segmentation of 2d and 3d mobile mapping data for reliable modeling of surface structures using deep learning |
| topic | mobile mapping systems road surface texture supervised learning semantic segmentation broadband infrastructure |
| url | https://www.mdpi.com/2072-4292/12/16/2530 |
| work_keys_str_mv | AT alexanderreiterer fullyautomatedsegmentationof2dand3dmobilemappingdataforreliablemodelingofsurfacestructuresusingdeeplearning AT katharinawaschle fullyautomatedsegmentationof2dand3dmobilemappingdataforreliablemodelingofsurfacestructuresusingdeeplearning AT dominikstork fullyautomatedsegmentationof2dand3dmobilemappingdataforreliablemodelingofsurfacestructuresusingdeeplearning AT achimleydecker fullyautomatedsegmentationof2dand3dmobilemappingdataforreliablemodelingofsurfacestructuresusingdeeplearning AT nikogitzen fullyautomatedsegmentationof2dand3dmobilemappingdataforreliablemodelingofsurfacestructuresusingdeeplearning |