ABSTRACT
The floor plan recognition problem is a sophistical and time-consuming task that requires architects to craft with their professional skills and tools. To solve Raster to vector (R2V) issues, this paper presents a deep-learning-based framework mainly consisting of YOLOv5, deep residual network (DRN), and OCR extraction algorithms. Our work can be interpreted in five steps: 1. Apply YOLOv5 to identify and separate a two-dimensional floor plan main body from the entire figure. Remove the annotation arrows by means of YOLOv5; 3. Extract the main structure data of the floor plan in the light of DRN;4. Apply OCR technology to read the annotation information; 5. Revise the floor plan to a real scale by means of the structured data from DRN recognition. The comparison experiment between our model and the original DRN model is carried out on the classical dataset RJFM (Recognition and 3D Reconstruction of Japan Residential Floor plan Model) and evaluated by a total of four loss functions, i.e. cross-entropy loss, near-neighbor field loss, endpoint regression loss, and multi-task loss. The results show that our model outperforms other methods in 2D floor plan recognition and further isometric 3D reconstruction.
- Fidler, S., Dickinson, S., & Urtasun, R. 2012. 3d object detection and viewpoint estimation with a deformable 3d cuboid model. Advances in neural information processing systems, 25, 611-619. https://dl.acm.org/doi/10.5555/2999134.2999203Google Scholar
- Alexander G. Schwing, Sanja Fidler, Marc Pollefeys, Raquel Urtasun. 2013. Box in the box: Joint 3d layout and object reasoning from single images. In Proceedings of the IEEE International Conference on Computer Vision. IEEE, Sydney, NSW, Australia, 353-360. https://doi.org/10.1109/ICCV.2013.51Google Scholar
- Zhang Y, He Y, Zhu S, Di X. 2020. The direction-aware, learnable, additive kernels and the adversarial network for deep floor plan recognition. arXiv preprint arXiv:2001.11194. https://arxiv.org/abs/2001.11194Google Scholar
- He K, Zhang X, Ren S, Sun J. Deep residual learning for image recognition. 2016. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 770-778. https://arxiv.org/abs/1512.03385Google Scholar
- Ahmed S, Liwicki M, Weber M, Dengel A. 2011. Improved automatic analysis of architectural floor plans. In Document Analysis and Recognition (ICDAR). 2011 International Conference on. IEEE, Beijing, China, 864–869. https://doi.org/10.1109/ICDAR.2011.177Google Scholar
- Ahmed S, Liwicki M, Weber M, Dengel A. 2012. Automatic room detection and room labeling from architectural floor plans. In 2012 10th IAPR International Workshop on Document Analysis Systems. IEEE, Gold Coast, QLD, Australia, 339-343. https://doi.org/10.1109/DAS.2012.22Google ScholarDigital Library
- Ahmed S, Weber M, Liwicki M, Dengel A. Text/graphics segmentation in architectural floor plans. 2011. In 2011 International Conference on Document Analysis and Recognition.IEEE, Beijing, China, 734-738. https://doi.org/10.1109/ICDAR.2011.153Google Scholar
- Tombre K, Tabbone S, Pélissier L, . Lamiroy B, and Dosch P. Text/graphics separation revisited.2002. In International Workshop on Document Analysis Systems. Springer, Berlin, Heidelberg, 200-211. https://doi.org/10.1007/3-540-45869-7_24Google Scholar
- Ahmed S, Liwicki M, Weber M, Dengel A. 2011. Improved automatic analysis of architectural floor plans. In 2011 International Conference on Document Analysis and Recognition. IEEE, Beijing, China, 864-869. https://doi.org/10.1109/ICDAR.2011.177Google ScholarDigital Library
- De las Heras, L. P., Ahmed, S., Liwicki, M., Valveny, E., & Sánchez, G. (2014). Statistical segmentation and structural recognition for floor plan interpretation. International Journal on Document Analysis and Recognition (IJDAR), 17(3), 221-237. https://doi.org/10.1007/s10032-013-0215-2Google ScholarDigital Library
- Macé S, Locteau H, Valveny E, and Tabbone S. (2010). A system to detect rooms in architectural floor plan images. In Proceedings of the 9th IAPR International Workshop on Document Analysis Systems, 167-174. https://doi.org/10.1145/1815330.1815352Google ScholarDigital Library
- Chen L C, Zhu Y, Papandreou G, Schroff F, Adam H. 2018. Encoder-decoder with atrous separable convolution for semantic image segmentation. In Proceedings of the European Conference on Computer Vision(ECCV), 801–818. https://arxiv.org/abs/1802.02611v1Google ScholarCross Ref
- Liu C, Schwing A G, Kundu K, , Urtasun R, and Fidler S. 2015. Rent3d: Floor-plan priors for monocular layout estimation. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. IEEE, Boston, MA, 3413-3421. https://doi.org/10.1109/CVPR.2015.7298963Google Scholar
- Martin-Brualla R, He Y, Russell B C, and Seitz S M. 2014. The 3d jigsaw puzzle: Mapping large indoor spaces. In European Conference on Computer Vision. Springer, Cham, 1-16. https://doi.org/10.1007/978-3-319-10578-9_1Google Scholar
- Chu H, Kim D K, Chen T. You are here: Mimicking the human thinking process in reading floor-plans. 2015. In Proceedings of the IEEE International Conference on Computer Vision. IEEE, Santiago, Chile, 2210-2218. https://doi.org/10.1109/ICCV.2015.255Google Scholar
- Wang S, Fidler S, Urtasun R. Lost shopping! monocular localization in large indoor spaces. 2015. In Proceedings of the IEEE International Conference on Computer Vision. IEEE, Santiago, Chile, 2695-2703. https://doi.org/10.1109/ICCV.2015.309Google Scholar
- Wijmans E, Furukawa Y. Exploiting 2d floorplan for building-scale panorama rgbd alignment. 2017. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. IEEE, Honolulu, HI, USA, 308-316. https://doi.org/10.1109/CVPR.2017.156Google Scholar
- Furukawa Y, Curless B, Seitz S M, and Szeliski R. 2009. Reconstructing building interiors from images. In 2009 IEEE 12th International Conference on Computer Vision. IEEE, Kyoto, Japan, 80-87. https://doi.org/10.1109/ICCV.2009.5459145Google ScholarCross Ref
- Choi S, Zhou Q Y, Koltun V. Robust reconstruction of indoor scenes. 2015. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, IEEE, Boston, MA, USA, 5556-5565. https://doi.org/10.1109/CVPR.2015.7299195Google Scholar
- Mura C, Mattausch O, Villanueva A J, Gobbetti E, and Pajarola R. 2014. Automatic room detection and reconstruction in cluttered indoor environments with complex room layouts. Computers & Graphics, 44:20-32. https://doi.org/10.1016/j.cag.2014.07.005Google Scholar
- Luo, X, O'Brien, W J, & Julien, C. L.. 2011. Comparative evaluation of Received Signal-Strength Index (RSSI) based indoor localization techniques for construction jobsites. Advanced Engineering Informatics, 25(2): 355-363. https://doi.org/10.1016/j.aei.2010.09.003Google Scholar
- Ikehata S, Yang H, Furukawa Y. 2015. Structured indoor modeling. In Proceedings of the IEEE International Conference on Computer Vision. IEEE, Santiago, Chile, 1323-1331. https://doi.org/10.1109/ICCV.2015.156Google ScholarDigital Library
- Yan, F, Nan, L, & Wonka, P. 2016. Block assembly for global registration of building scans. ACM Transactions on Graphics (TOG), 35(6), 1-11. https://doi.org/10.1145/2980179.2980241Google ScholarDigital Library
- Liu C, Wu J, Kohli P, Furukawa Y. 2017. Raster-to-vector: Revisiting floorplan transformation. In Proceedings of the IEEE International Conference on Computer Vision. IEEE, Venice, Italy, 2195-2203. https://doi.org/10.1145/2980179.2980241Google ScholarCross Ref
- LIFULL HOME'S dataset. https://www.homes.co.jp/Google Scholar
- Long J, Shelhamer E, Darrell T. 2015. Fully convolutional networks for semantic segmentation. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 3431-3440. https://arxiv.org/abs/1411.4038Google ScholarCross Ref
- Macé S, Locteau H, Valveny E, Tabbone S. 2010. A system to detect rooms in architectural floor plan images. In Proceedings of the 9th IAPR International Workshop on Document Analysis Systems, 167-174. https://doi.org/10.1145/1815330.1815352Google ScholarDigital Library
- Ramer U. 1972. An iterative procedure for the polygonal approximation of plane curves. Computer Graphics and Image Processing, 1(3): 244-256. https://doi.org/10.1016/S0146-664X(72)80017-0Google Scholar
- Zeng Z, Li X, Yu Y K, Fu C. 2019. Deep floor plan recognition using a multi-task network with room-boundary-guided attention. In Proceedings of the IEEE/CVF International Conference on Computer Vision. IEEE, Seoul, Korea (South), 9096-9104. https://doi.org/10.1109/ICCV.2019.00919Google ScholarCross Ref
- Baek Y, Lee B, Han D, Yun S, and Lee H. 2019. Character region awareness for text detection. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. IEEE, Long Beach, CA, USA, 9365-9374. https://doi.org/10.1109/CVPR.2019.00959Google Scholar
- Lv X, Zhao S, Yu X, Zhao B. Residential floor plan recognition and reconstruction. 2021. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. IEEE, Nashville, TN, USA, 16717-16726. https://doi.org/10.1109/CVPR46437.2021.01644Google Scholar
- Liu S, Li T, Chen W, Li H. 2019. Soft rasterizer: A differentiable renderer for image-based 3d reasoning. In Proceedings of the IEEE/CVF International Conference on Computer Vision. IEEE, Seoul, Korea (South), 7708-7717. https://doi.org/10.1109/ICCV.2019.00780Google ScholarCross Ref
Recommendations
Knowledge-driven description synthesis for floor plan interpretation
AbstractImage captioning is a widely known problem in the area of AI. Caption generation from floor plan images has applications in indoor path planning, real estate, and providing architectural solutions. Several methods have been explored in the ...
A graph-theoretic approach to constrained floor plan estimation from radar measurements
This paper proposes an approach to deducing the floor plan of a building using only a set of noisy room dimension measurements that have been obtained indirectly through radar probes. It is not assumed that the set of measurements is complete. The key ...
RISC-Net : rotation invariant siamese convolution network for floor plan image retrieval
AbstractA floor plan represents the blue print of a building. Organizing a massive set of such floor plans and accessing them based on similarity is challenging for any architect. During the digitization process printed floor plan images are rotated ...
Comments