AIRR  >> Vol. 2 No. 1 (February 2013)

    阴影恢复形状技术研究进展
    A Survey of Research Work on Shape from Shading

  • 全文下载: PDF(447KB)    PP.48-53   DOI: 10.12677/AIRR.2013.21008  
  • 下载量: 1,651  浏览量: 7,224  

作者:  

邵晓芳:海军航空工程学院青岛校区,青岛;
蔡明娟:海军装备研究院标准所,上海

关键词:
阴影恢复形状三维表面重构深度图Shape from Shading; 3D Surface Reconstruction; Depth Map

摘要:

根据单幅灰度图像恢复相应物体的三维表面形状是计算机视觉中的一个基本问题,也是一个重要研究领域,相当于完成一个从二维空间到三维空间的映射,解决这类问题的一个重要方法是从阴影恢复形状(Shape from Shading,简称SFS)。从问题描述入手,对阴影恢复形状技术涉及基本问题和现有计算方法进行了分类总结并分析了现有方法的特点和不足,最后指出了进一步研究的发展方向。

The reconstruction for 3D surface shape of object is one of the main goals in the field of computer vision. It needs to complete a mapping from 2D image to 3D world. Shape from shading (SFS for short) is one of the main meth-ods for this goal. This paper gives a comprehensive summary on related research work based on the description of the SFS problem, then their characteristics and shortcomings are analyzed; at last, further research directions are suggested.

文章引用:
邵晓芳, 蔡明娟. 阴影恢复形状技术研究进展[J]. 人工智能与机器人研究, 2013, 2(1): 48-53. http://dx.doi.org/10.12677/AIRR.2013.21008

参考文献

[1] B. K. P. Horn, M. J. Brooks. Shape from shading. Cambridge: MIT Press, 1989.
[2] 王怀颖. 细胞神经网络在图像处理中的应用技术研究[D]. 南京航空航天大学, 2007.
[3] O. Vogel, M. Breuß and J. Weickert. Perspective shape from shading with non-Lambertian reflec-tance. Proceedings of the 30th DAGM symposium on Pattern Recogni-tion, 2008: 517-526.
[4] Q. H. Zhu, J. B. Shi. Shape from shading: Recognizing the mountains through a global view. Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2006, 1: 1-8.
[5] 蔻镇淳. 从明暗恢复形状的有理样条方法[D]. 大连理工大学, 2005.
[6] K. M. Lee, C. C. J. Kuo. Shape from shading with a linear triangular element surface model. IEEE Transaction on Pattern Analysis and Machine Intelligence, 1993, 15(8): 815-822.
[7] C. H. Lee, A. Rosenfeld. Improved methods of estimating shape from shading using the light source coordinate system. Artificial Intelligence, 1985, 26: 125-143.
[8] J. Oliensis. Shape from shading as a partially well-constrained problem. Computer Vision, Graphics, and Image Processing: Image Understanding, 1991, 54: 163-183.
[9] J. Malik, D. Maydan. Recovering three dimensional shape from a single image of curved objects. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1989, 11: 213-224.
[10] V. S. Ramachandran Perceiving shape from shading. Scientific American, 1988, 159: 76-83.
[11] M. Ben-Ezra, S. K. Nayar. What does motion reveal about trans- parency. Proceedings of the 9th IEEE International Conference on Computer Vision, IEEE Computer Society, 2003, 1: 1025- 1028.
[12] H. Ragheb, E. R. Hancock. A probabilistic frame-work for spe- cular shape-from-shading. International Conference on Pattern Recognition, 2002, 3: 513-516.
[13] Q. Zheng, R. Chellappa. Estimation of illuminant direction, albedo, and shape from shading. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1991, 13(7): 680-702.
[14] R. White,D. A. Forsyth. Combining cues: Shape from shading and texture. Computer Vision and Pattern Recognition, 2006, 2: 1809-1816.
[15] O. Vogel, L. Valgaerts, M. Breuß and J. Weickert. Making shape from shading work for real-world images. DAGM-Symposium, 2009: 191-200.
[16] A. Pentland. Shape infor-mation from shading: A theory about human perception. Proceedings of International Conference on Computer Vision, 1988, 1: 404-413.
[17] P. S. Tsai, M. Shah. Shape from shading using linear approxi- mation. Image and Vision Computing Journal, 1994, 12(8): 487- 498.
[18] E. Rouy, A. Tourin. A viscosity solutions approach to shape from shading. SIAM Journal on Numerical Analysis, 1992, 29(3): 867-884.
[19] M. Bichsel, A. P. Pentland. A simple algorithm for shape from shading. IEEE Proceedings of Computer Vision and Pattern Re- cognition, 1992, 1: 459-465.
[20] R. Kimmel, A. M. Bruckstein. Shape from shading via level sets. Israel Institute of Technology, CIS Report 9209, 1992.
[21] J. Oliensis, P. Dupuis. A global algorithm for shape from shading. Proceedings of International Conference on Computer Vision, 1993, 1: 692-701.