Gutbell, Ralf ; Kuehnel, Hannes ; Kuijper, Arjan (2017)
Texturizing and Refinement of 3D City Models with Mobile Devices.
ACIVS 2017 : 18th International Conference. Antwerp, Belgium (18.09.2017-21.09.2017)
doi: 10.1007/978-3-319-70353-4_27
Konferenzveröffentlichung, Bibliographie
Kurzbeschreibung (Abstract)
Building recognition from images and video streams of mobile devices to texturize and refine an existing 3D city model is an open challenge, since such models most often do not completely represent the actual buildings. We present ways to extract buildings from images enabling improvement of the existing model. The approach is based on edge detection on images to detect walls, pure use of sensor data by creating an overlay to the video stream with the 3D model renderer from current position by a server, and the use of structure from motion algorithms to create point clouds and recognize a building via the support of the device's sensors. We show that we are thus able to texturize and refine an existing 3D city model.
| Typ des Eintrags: | Konferenzveröffentlichung |
|---|---|
| Erschienen: | 2017 |
| Autor(en): | Gutbell, Ralf ; Kuehnel, Hannes ; Kuijper, Arjan |
| Art des Eintrags: | Bibliographie |
| Titel: | Texturizing and Refinement of 3D City Models with Mobile Devices |
| Sprache: | Englisch |
| Publikationsjahr: | 2017 |
| Ort: | Berlin |
| Verlag: | Springer |
| Buchtitel: | Advanced Concepts for Intelligent Vision Systems : Proceedings |
| Veranstaltungstitel: | ACIVS 2017 : 18th International Conference |
| Veranstaltungsort: | Antwerp, Belgium |
| Veranstaltungsdatum: | 18.09.2017-21.09.2017 |
| DOI: | 10.1007/978-3-319-70353-4_27 |
| URL / URN: | https://doi.org/10.1007/978-3-319-70353-4_27 |
| Kurzbeschreibung (Abstract): | Building recognition from images and video streams of mobile devices to texturize and refine an existing 3D city model is an open challenge, since such models most often do not completely represent the actual buildings. We present ways to extract buildings from images enabling improvement of the existing model. The approach is based on edge detection on images to detect walls, pure use of sensor data by creating an overlay to the video stream with the 3D model renderer from current position by a server, and the use of structure from motion algorithms to create point clouds and recognize a building via the support of the device's sensors. We show that we are thus able to texturize and refine an existing 3D city model. |
| Freie Schlagworte: | Structure-from-Motion (SfM), Self calibration, Multi-view stereo, 3D Reconstruction, Image-based rendering, 3D City models, 3D Computer vision |
| Zusätzliche Informationen: | Lecture Notes in Computer Science, vol 10617 |
| Fachbereich(e)/-gebiet(e): | 20 Fachbereich Informatik 20 Fachbereich Informatik > Mathematisches und angewandtes Visual Computing |
| Hinterlegungsdatum: | 05 Mai 2020 14:18 |
| Letzte Änderung: | 05 Mai 2020 14:18 |
| PPN: | |
| Export: | |
| Suche nach Titel in: | TUfind oder in Google |
 |
Frage zum Eintrag |
Optionen (nur für Redakteure)
 |
Redaktionelle Details anzeigen |
Drucken
Impressum