| 275 | 0 | 116 |
| 下载次数 | 被引频次 | 阅读次数 |
提取房屋结构是重建三维房屋的基础工作，主要被应用在虚拟现实（virtual reality,VR）看房、在线家装设计等新兴领域。针对户型图风格多样以及传统图像处理方法自动化程度低、普适性差的问题，提出一种结合深度学习和图像处理的方法，先通过深度学习方法获取墙、门和窗户在图像中的位置信息，再通过图像处理方法获得矢量化结果。在二维户型图上进行实验，结果表明了所提户型图矢量化方法的有效性和适用性。
Abstract：Extracting the structure of a house is the basic work of reconstructing a 3D house. It is mainly used in the emerging fields such as virtual reality(VR) house viewing and online house decoration design. Aiming at the problems of various styles of floorplan images and the low automation and poor generality of the traditional image processing methods, we propose a method that combines deep learning and image processing. First, the position information of the walls, doors, and windows in the images are obtained by deep learning method, and then the vectorization results are obtained by image processing method. Experiments are performed on the 2D floorplan images. The results show the effectiveness and applicability of the proposed vectorization method.
[1] Moloo R K, Dawood M A S, Auleear A S. 3-Phase Recognition Approach to Pseudo 3D Building Generation from 2D Floor Plan[J]. International Journal of Computer Graphics&Animation(IJCGA),2011,1:2
[2] Or S H, Wong K H, Yu Y K, et al. Highly Automatic Approach to Architectural Floorplan Image Understanding&Model Generation[J]. Pattern Recognition, 2008, 2(3):210-225
[3]朱俊芳.基于结构构件识别的户型图三维重建算法研究[D].北京：清华大学，2013
[4]肖毅，李攀，刘旭晔，等.基于OpenCV的三维户型图智能重建[J].信息与电脑（理论版），2018(6):35-36
[5]江州.基于形状与边缘特征的户型图识别研究[D].哈尔滨：哈尔滨工业大学，2017
[6]黄文.面向自动家装生成的户型图识别方法研究[D].合肥：合肥工业大学，2018
[7] Guo T T, Zhang H, Wen Y M. An Improved ExampleDriven Symbol Recognition Approach in Engineering Drawings[J]. Computers&Graphics, 2012, 36(7):835-845
[8] Wen Y D, Zhang K P, Li Z F, et al. A Discriminative Feature Learning Approach for Deep Face Recognition[C]. Computer Vision-ECCV 2016, Amsterdam, The Netherlands, 2016
[9] Sun Y, Liang D, Wang X G, et al. DeepID3:Face Recognition with Very Deep Neural Networks[EB/OL].[2019-11-20]. https：//doi. org/10. 48550/arXiv. 1502. 00873
[10] Shelhamer E, Long J, Darrell T. Fully Convolutional Networks for Semantic Segmentation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 39(4):640-651
[11] Chen L C, Papandreou G, Kokkinos I, et al. DeepLab:Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2018,40(4):834-848
[12] Girshick R, Donahue J, Darrell T, et al. Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation[C]. IEEE Conference on Computer Vision and Pattern Recognition(CVPR),Columbus,OH,USA, 2014
[13] Ren S Q, He K M, Girshick R, et al. Faster R-CNN:Towards Real-Time Object Detection with Region Proposal Networks[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 39(6):1 137-1 149
[14] Shih K H, Chiu C T, Lin J A, et al. Real-Time Object Detection with Reduced Region Proposal Network via Multi-feature Concatenation[J]. IEEE Transactions on Neural Networks and Learning Systems,2020, 31(6):2 164-2 173
[15] He K M, Gkioxari G, Dollár P, et al. Mask R-CNN[C]. 2017 IEEE International Conference on Computer Vision(ICCV), Venice, Italy, 2017
[16] Zhou Y C, Qi H Z, Ma Y. End-to-End Wireframe Parsing[C]. 2019 IEEE/CVF International Conference on Computer Vision(ICCV), Seoul, R. O. Korea,2019
基本信息:
DOI：10.14188/j.2095-6045.2020110
中图分类号:TP391.9;TU204
引用信息:
[1]孙薇薇,蒋佳芹,姚剑.一种基于深度学习的户型图矢量化方法[J].测绘地理信息,2023,48(03):55-59.DOI:10.14188/j.2095-6045.2020110.
基金信息: