Advertisement

Three-Dimensional Structure Measurement and Optimization Method of Indoor Scene Based on Single Image

  • Ronghe WangEmail author
  • Xinhai Zhang
  • Bo Zhang
  • Jianning Bi
  • Xiaolei Guo
Conference paper
Part of the Lecture Notes in Electrical Engineering book series (LNEE, volume 517)

Abstract

In the paper, we detect 2D surfaces and recognize 3D structures in images, and generate occluded part of three-dimensional structure. We detect objects vanish points and geometric segmentation lines, and generate the vector and normal plane. We measure the objects boundaries which have been detected. In the process, we have found the best linear segmentation positions, generated buildings, and other 3D models in room. We propose some effective assumptions to recognize the object model from images by geometric reasoning. At the same time, we put forward structure prediction technology combined with the volume reasoning by parameter representation of spatial objects. We detect scene model relationships of each other by combining image-rich appearance with geometric features. We proposed image geometric modeling grammar framework according to previous discriminative classifier. It is used to represent the physical structure of the visual component. The framework has broken the traditional probability texture context grammar tree model. We proposed spatial context theory and model generation rules. Finally, on the public existing data sets, we proved that we only use structure prediction and linear segmentation of scene to recover 3D structure by a lot of experiments, comparing to restoration algorithm using whole image structure, ours method can produce more credible scene entity models and space constraint relationships.

Keywords

Models detection Geometric reasoning Energy minimization method Models generation Scene grammar model 

Notes

Acknowledgements

We sincerely thank the reviewers and editors’ work to this paper. This paper is supported by National Natural Science Foundation Projects of China, the national key research and development program of china: Research and development of intelligent security card port monitoring and warning platform (Grant No. 2016YFC0800507), Innovation Foundation Program of China Electronics Technology Group Corporation: Research on holographic and abnormal behavior intelligent warning technology for social security risk targets.

References

  1. 1.
    Gupta, A., Satkin, S., Efros, A.A., Hebert, M.: From 3d scene geometry to human workspace. In: CVPR (2011)Google Scholar
  2. 2.
    Lee, D., Gupta, A., Hebert, M., Kanade, T.: Estimating the spatial layout of rooms using volumetric reasoning about objects and surfaces. In: NIPS (2010)Google Scholar
  3. 3.
    Hedau, V., Hoiem, D., Forsyth, D.: Recovering the spatial layout of cluttered rooms. In: ICCV (2009)Google Scholar
  4. 4.
    Tu, Z., Bai, X.: Auto-context and its application to high-level vision tasks and 3d brain image segmentation. PAMI (2009)Google Scholar
  5. 5.
    Saxena, A., Sun, M., Ng, A.: Make3d: learning 3d scene structure from a single image. PAMI (2008)Google Scholar
  6. 6.
    Lee, D., Gupta, A., Hebert, M., Kanade, T.: Estimating spatial layout of rooms using volumetric reasoning about objects and surfaces. In: Advances in Neural Information Processing Systems, vol. 7, pp. 609–616. MIT Press, Cambridge, MA (2010)Google Scholar
  7. 7.
    Wang, H., Gould, S., Koller, D.: Discriminative learning with latent variables for cluttered indoor scene understanding. In: ECCV (2010)Google Scholar
  8. 8.
    Hedau, V., Hoiem, D., Forsyth, D.: Recovering the spatial layout of cluttered rooms. In ICCV (2009)Google Scholar
  9. 9.
    Han, F., Zhu, S.C.: Bottom-up/top-down image parsing with attribute grammar. PAMI (2009)Google Scholar
  10. 10.
    Porway, J., Zhu, S.C.: C4: computing multiple solutions in graphical models by cluster sampling. PAMI 33(9), 1713–1727 (2011)CrossRefGoogle Scholar
  11. 11.
    Saxena, M.S., Ng, A.: Make3d: learning 3d scene structure from a single image. PAMI (2008)Google Scholar
  12. 12.
    Delage, E., Lee, H., Ng, A.: A dynamic bayesian network model for autonomous 3d reconstruction from a single indoor image. CVPR (2006)Google Scholar
  13. 13.
    Han, F., Zhu, S.: Bottom-up/top-down image parsing by attribute graph grammar. In: Proceedings of International Conference on Computer Vision (ICCV) (2005)Google Scholar
  14. 14.
    Lee, D., Hebert, M., Kanade, T.: Geometric reasoning for single image structure recovery. In: Proceedings of CVPR (2009)Google Scholar
  15. 15.
    Hedau, V., Hoiem, D., Forsyth, D.: Recovering the spatial layout of cluttered rooms. In: Proceedings of ICCV (2009)Google Scholar
  16. 16.
    Hedau, V., Hoiem, D., Forsyth, D.: Thinking inside the box: using appearance models and context based on room geometry. In: ECCV (2010)Google Scholar
  17. 17.
    Denis, P., Elder, J.H., Estrada, F.: Efficient edge-based methods for estimating manhattan frames in urban imagery. In: ECCV (2008)Google Scholar
  18. 18.
    Delage, E., Lee, H., Ng, A.Y.: A dynamic bayesian network model for autonomous 3d reconstruction from a single indoor image. In: CVPR (2006)Google Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2020

Authors and Affiliations

  • Ronghe Wang
    • 1
    Email author
  • Xinhai Zhang
    • 1
  • Bo Zhang
    • 1
  • Jianning Bi
    • 1
  • Xiaolei Guo
    • 1
  1. 1.National Engineering Laboratory for Public Security Risk Perception and Control by Big Data (PSRPC), China Academy of Electronics and Information TechnologyChina Electronics Technology Group CorporationShijingshan District, BeijingPeople’s Republic of China

Personalised recommendations