A Study of Generating Depth map for 3D Space Structure Recovery

  • Ban, Kyeong-Jin (Department of Computer Science, Sunchon University) ;
  • Kim, Jong-Chan (Department of Computer Science, Sunchon University) ;
  • Kim, Eung-Kon (Department of Computer Science, Sunchon University) ;
  • Kim, Chee-Yong (Department of Visual Information Engineering, DongEui University)
  • Received : 2010.12.10
  • Accepted : 2010.12.29
  • Published : 2010.12.30

Abstract

In virtual reality, there are increasing qualitative development in service technologies for realtime interaction system development, 3- dimensional contents, 3D TV and augment reality services. These services experience difficulties to generate depth value that is essential to recover 3D space to form solidity on existing contents. Hence, research for the generation of effective depth-map using 2D is necessary. This thesis will describe a shortcoming of an existing depth-map generation for the recovery of 3D space using 2D image and will propose an enhanced depth-map generation algorithm that complements a shortcoming of existing algorithms and utilizes the definition of depth direction based on the vanishing point within image.

Keywords

References

  1. R. T. Azuma, "A survey of Augmented Reality," In presence: Teleoperators and Virtual Environment, Vol. 6, no. 4, pp.355-385, Aug 1997. https://doi.org/10.1162/pres.1997.6.4.355
  2. K. Sugihara, "Three Principle in Stereo Vision," Robotics, Vol. 1, No. 4, pp.391-400, 1986. https://doi.org/10.1163/156855386X00256
  3. R. Mohr, "Projective Geometry And Computer Vision," Handbook of Pattern Recognition and Computer Vision, World Scientific, Singapore, pp.369-393, 1993.
  4. J. Kogecka, W. Zhang, "Efficient Computation of Vanishing Points," ICRA 2002, Vol. 1, pp.223-228, 2002.
  5. C. Rother, "A New Approach for Vanishing Point Detection in Architectural Environments," Image and Vision Computing 2002, Vol. 20, pp.647-655, Aug, 2002. https://doi.org/10.1016/S0262-8856(02)00054-9
  6. R, M. Hatralick and L. G, Shapiro,"Computer And Robot Vision", Addison I Wesley Publishing Ca, 1993.
  7. S. D. Ma, "Conies-based stereo, motion estimation, and pose determination," Intern. J. Compute, Vision, Vol. 10, no. 1, pp. 7-25, 1993. https://doi.org/10.1007/BF01440844
  8. J. A. Shufelt, "Performance Evaluation and Analysis of Vanishing Point Detection Techniques," Proc. ARPA Image Understanding Workshop, pp.1113-1132, 1996.
  9. D. A. Forsyth, "Shape from texture without boundaries," Lecture Notes in Computer Science, Vol. 2352, pp. 43-66, 2002
  10. C. Rasmussen and B. machine, "Texture- Based Vanishing Point Voting for Road Shape Estimation. Proc. British Machine Vision Conference, Vol. 1, pp. 47–56. 5, 2004.
  11. A. Saxena, S. H. Chung, and Y. Ng. Andrew, "Learning Depth from Single Monocular Images," Proc. 19th Ann. Conf. Neural Information Processing Systems, Vol. 18, 2006.
  12. T. Hassner and R. Basri, "Example Based 3D Reconstruction from Single 2D Images," In CVPR workshop on Beyond Patches, 2006.
  13. A. Saxena, S. H. Chung, and Y. N. Andrew, "3D Depth Reconstruction from a Single Still Image", Int J Comput Vis 76, pp. 53-69, 2008.
  14. A. Saxena, S. H. Chung, and Y. N. Andrew, "Learning 3D Scene Structure from a Single Still Image" IEEE Transactions on Pattern Analysis Machine Intelligence, Vol. 31, no. 5, pp. 824-840, May, 2009. https://doi.org/10.1109/TPAMI.2008.132
  15. K. J. Ban, J. C. Kim, E. K. Kim," An Object Representation System Using Virtual Spac.