Advertisement

Thinking Inside the Box: Using Appearance Models and Context Based on Room Geometry

  • Varsha Hedau
  • Derek Hoiem
  • David Forsyth
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6316)

Abstract

In this paper we show that a geometric representation of an object occurring in indoor scenes, along with rich scene structure can be used to produce a detector for that object in a single image. Using perspective cues from the global scene geometry, we first develop a 3D based object detector. This detector is competitive with an image based detector built using state-of-the-art methods; however, combining the two produces a notably improved detector, because it unifies contextual and geometric information. We then use a probabilistic model that explicitly uses constraints imposed by spatial layout – the locations of walls and floor in the image – to refine the 3D object estimates. We use an existing approach to compute spatial layout [1], and use constraints such as objects are supported by floor and can not stick through the walls. The resulting detector (a) has significantly improved accuracy when compared to the state-of-the-art 2D detectors and (b) gives a 3D interpretation of the location of the object, derived from a 2D image. We evaluate the detector on beds, for which we give extensive quantitative results derived from images of real scenes.

Keywords

Spatial Layout Indoor Scene Object Hypothesis Camera Height Scene Layout 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

References

  1. 1.
    Hedau, V., Hoiem, D., Forsyth, D.A.: Recovering the spatial layout of cluttered rooms. In: Proc. ICCV (2009)Google Scholar
  2. 2.
    Sung, K.K., Poggio, T.: Example based learning for view-based human face detection. Technical report, Cambridge, MA, USA (1994)Google Scholar
  3. 3.
    Rowley, H.A., Baluja, S., Kanade, T.: Neural network-based face detection. In: CVPR, p. 203. IEEE Comp. Society, Los Alamitos (1996)Google Scholar
  4. 4.
    Schneiderman, H., Kanade, T.: A statistical model for 3-d object detection applied to faces and cars. In: CVPR (2000)Google Scholar
  5. 5.
    Viola, P., Jones, M.J.: Robust real-time face detection. IJCV 57 (2004)Google Scholar
  6. 6.
    Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: CVPR (2005)Google Scholar
  7. 7.
    Felzenszwalb, P.F., Girshick, R.B., McAllester, D., Ramanan, D.: Object detection with discriminatively trained part based models. PAMI 99 (2009)Google Scholar
  8. 8.
    Hoiem, D., Rother, C., Winn, J.: 3d layoutcrf for multi-view object class recognition and segmentation. In: CVPR (2007)Google Scholar
  9. 9.
    Su, H., Sun, M., Fei-Fei, L., Savarese, S.: Learning a dense multi-view representation for detection, viewpoint classification and synthesis of object categories. In: ICCV, Kyoto, Japan (2009)Google Scholar
  10. 10.
    Saxena, A., Sun, M., Ng, A.Y.: Make3d: Learning 3-d scene structure from a single still image. In: PAMI (2008)Google Scholar
  11. 11.
    Lee, D., Hebert, M., Kanade, T.: Geometric reasoning for single image structure recovery. In: Proc. CVPR (2009)Google Scholar
  12. 12.
    Hoiem, D., Efros, A.A., Hebert, M.: Recovering surface layout from an image. IJCV 75 (2007)Google Scholar
  13. 13.
    Barinova, O., Konushin, V., Yakubenko, A., Lee, K., Lim, H., Konushin, A.: Fast automatic single-view 3-d reconstruction of urban scenes. In: Forsyth, D., Torr, P., Zisserman, A. (eds.) ECCV 2008, Part II. LNCS, vol. 5303, pp. 100–113. Springer, Heidelberg (2008)CrossRefGoogle Scholar
  14. 14.
    Gupta, A., Efros, A.A., Hebert, M.: Blocks world revisited: Image understanding using qualitative geometry and mechanics. In: ECCV (2010)Google Scholar
  15. 15.
    Hoiem, D., Efros, A.A., Hebert, M.: Closing the loop on scene interpretation. In: Proc. CVPR (2008)Google Scholar
  16. 16.
    Gould, S., Fulton, R., Koller, D.: Decomposing a scene into geometric and semantically consistent regions. In: ICCV (2009)Google Scholar
  17. 17.
    Sudderth, E., Torralba, A., Freeman, W.T., Wilsky, A.: Depth from familiar objects: A hierarchical model for 3D scenes. In: Proc. CVPR (2006)Google Scholar
  18. 18.
    Heitz, G., Gould, S., Saxena, A., Koller, D.: Cascaded classification models: Combining models for holistic scene understanding. In: Koller, D., Schuurmans, D., Bengio, Y., Bottou, L. (eds.) NIPS, pp. 641–648. MIT Press, Cambridge (2008)Google Scholar
  19. 19.
    Yu, S., Zhang, H., Malik, J.: Inferring spatial layout from a single image via depth-ordered grouping. In: CVPR Workshop (2008)Google Scholar
  20. 20.
    Tu, Z., Chen, X., Yuille, A.L., Zhu, S.C.: Image parsing: Unifying segmentation, detection, and recognition. IJCV 63, 113–140 (2005)CrossRefGoogle Scholar
  21. 21.
    Hoiem, D., Efros, A.A., Hebert, M.: Putting objects in perspective. In: CVPR (2006)Google Scholar
  22. 22.
    Leibe, B., Schindler, K., Cornelis, N., van Gool, L.: Coupled object detection and tracking from static cameras and moving vehicles. PAMI 30, 1683–1698 (2008)Google Scholar
  23. 23.
    Rother, C.: A new approach to vanishing point detection in architectural environments. IVC 20 (2002)Google Scholar
  24. 24.
    Russell, B., Torralba, A., Murphy, K., Freeman, W.: Labelme: A database and web-based tool for image annotation. IJCV 77 (2008)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2010

Authors and Affiliations

  • Varsha Hedau
    • 1
  • Derek Hoiem
    • 2
  • David Forsyth
    • 2
  1. 1.Department of Electrical and Computer EngineeringUniversity of Illinois at Urbana Champaign 
  2. 2.Department of Computer ScienceUniversity of Illinois at Urbana Champaign 

Personalised recommendations