This Article 
 Bibliographic References 
 Add to: 
An Error Analysis for Surface Orientation from Vanishing Points
December 1990 (vol. 12 no. 12)
pp. 1179-1185

Given two parallel lines in a plane, their images formed by central projection onto the viewing plane intersect at a vanishing point, which provides a constraint on the orientation of the plane. Two such independent constraints define a vanishing line and thereby determine the orientation of the plane uniquely. In order to effectively use this information, an estimate of its accuracy must be incorporated. In the approach suggested, line directions and surface normal vectors are represented as points on a Gaussian sphere, and the error bounds are computed as regions on the sphere. Information from multiple vanishing points and surfaces is combined by intersecting the corresponding regions. In addition, constraints based on real-world knowledge can be introduced to improve the accuracy. Some experimental results on natural images re presented to illustrate this method.

[1] S. T. Barnard, "Interpreting perspective images,"AI Journal, vol. 21, no. 4, pp. 435-462, Nov. 1983.
[2] J. Burns, A. Hanson, and E. Riseman, "Extracting straight lines,"IEEE Trans. Patt. Anal. Machine Intell., vol. PAMI-8, no. 4, pp. 425-455, July 1986.
[3] R. Collins and R. Weiss, "An efficient and accurate method for computing vanishing points," inProc. Opt. Soc. Amer. Workshop Image Understanding and Machine Vision, vol. 14, June 1989, pp. 92-94.
[4] M. Herman, T. Kanade, and S. Kuroe, "Incremental acquisition of a three-dimensional scene model from images,"IEEE Trans. Pattern Anal. Machine Intell., vol. PAMI-6, no. 3, pp. 331-340, May 1984.
[5] W. E. L. Grimson and T. Lozano-Pérez, "Model-based recognition and localization from sparse range or tactile data,"Int. J. Robotics Res., vol. 3, no. 3, pp. 3-35, Fall 1984.
[6] R. Horaud, "New methods for matching 3-D objects with single perspective views,"IEEE Trans. Patt. Anal. Machine Intell., vol. PAMI-9, pp. 401-412, May 1987.
[7] K. Kanatani, "Camera rotation invariance of image characteristics,"Comput. Vision Graphics Image Processing, vol. 39, pp. 328-354, 1987.
[8] M. J. Magee and J. K. Aggarwal, "Determining vanishing points from perspective images,"Comput. Vision, Graphics, Image Processing, vol. 26, pp. 256-267, 1984.
[9] H. Nakatani, S. Kimura, O. Saito, and T. Kitahashi, "Extraction of vanishing point and its application to scene analysis based on image sequence," inProc. 5th Int. Conf. Pattern Recognition, 1980, pp. 370-372.
[10] H. Nakatani and T. Kitahashi, "Inferring 3-D shape from line drawings using vanishing points," inProc. 1st Int. Conf. Computers and Applications, 1984.
[11] H. Nakatani, "Reconstruction of three-dimensional shape using pictorial depth cues," Ph.D. dissertation, Osaka Univ., 1986.
[12] H. Nakatani, R. Weiss, and E. Riseman, "Application of vanishing points to 3-D measurement,"Proc. SPIE, vol. 507, pp. 164-169, 1984.

Index Terms:
picture processing; pattern recognition; error analysis; surface orientation; vanishing points; parallel lines; surface normal vectors; Gaussian sphere; error analysis; pattern recognition; picture processing
R.S. Weiss, H. Nakatani, E.M. Riseman, "An Error Analysis for Surface Orientation from Vanishing Points," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 12, no. 12, pp. 1179-1185, Dec. 1990, doi:10.1109/34.62606
Usage of this product signifies your acceptance of the Terms of Use.