| Title: | Line Clustering and Contour Extraction in the Context of 2D Building Plans |
| Authors: | Pointner, Andreas Praschl, Christoph Krauss, Oliver Schuler, Andreas Helm, Emmanuel Zwettler, Gerald |
| Citation: | WSCG 2021: full papers proceedings: 29. International Conference in Central Europe on Computer Graphics, Visualization and Computer Vision, p. 11-20. |
| Issue Date: | 2021 |
| Publisher: | Václav Skala - UNION Agency |
| Document type: | conferenceObject konferenční příspěvek |
| URI: | http://hdl.handle.net/11025/45005 |
| ISBN: | 978-80-86943-34-3 |
| ISSN: | 2464-4617 2464–4625(CD/DVD) |
| Keywords: | shlukování;extrakce obrysů;stavební plán;zpracování obrazu;strojové učení |
| Keywords in different language: | clustering;contour extraction;building plan;image processing;machine learning |
| Abstract in different language: | For the purpose of analyzing a building according to its accessibility or structural resilience, printed 2D floorplans are not sufficient because of the missing link to semantic information. This paper tackles this issue andintroduces a concept for clustering classified lines of a floor plan and for creating semantically enriched contourelements based on different image processing, computer vision and machine learning algorithms. Based on ageneral line clustering approach, we introduce type specific methods forwalls,windows,doorsandstairs. Theresulting clusters are in turn used for a contour creation, which uses minimal rotated rectangles. Those rectanglesare transformed to polygons that are refined using post processing steps. The approach is evaluated via positivetesting using a pixel-based comparison of the process’s result. For this, automatically generated as well as realworld building plans are used. The final evaluation shows, that the concept reaches a confidence of >90% for door,stair and windows and only around 10% for stairs with the run-time linearly scaling with the size of the input. |
| Rights: | © Václav Skala - UNION Agency |
| Appears in Collections: | WSCG 2021: Full Papers Proceedings |
Please use this identifier to cite or link to this item:
http://hdl.handle.net/11025/45005Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.