Robust estimation of depth and motion using stochastic approximation

The problem of structure from motion (SfM) is to extract the three-dimensional model of a moving scene from a sequence of images. Though two images are sufficient to produce a 3D reconstruction, they usually perform poorly because of errors in the estimation of the camera motion and image correspondences, thus motivating the need for multiple frame algorithms. One common approach to this problem is to determine the estimate from pairs of images and then fuse them together. Data fusion techniques, like the Kalman filter, require estimates of the error in modeling and observations. The complexity of the SfM problem makes it difficult to reliably estimate these errors. This paper describes a new recursive algorithm to estimate the camera motion and scene structure by fusing the two-frame estimates, using stochastic approximation techniques. The method does not require estimates of the error in the two-frame case and can reconstruct the scene to arbitrary accuracy given a sufficient number of frames. Experimental results are reported to support these claims.

[1]  Vishvjit S. Nalwa,et al.  A guided tour of computer vision , 1993 .

[2]  H. Vincent Poor,et al.  An Introduction to Signal Detection and Estimation , 1994, Springer Texts in Electrical Engineering.

[3]  S. T. Buckland,et al.  An Introduction to the Bootstrap. , 1994 .

[4]  John Oliensis,et al.  A Critique of Structure-from-Motion Algorithms , 2000, Comput. Vis. Image Underst..

[5]  ZhangZhengyou.  Determining the Epipolar Geometry and its Uncertainty , 1998 .

[6]  P. Rousseeuw.  Least Median of Squares Regression , 1984 .

[7]  J. Spall.  Resampling-based calculation of the information matrix for general identification problems , 1998, Proceedings of the 1998 American Control Conference. ACC (IEEE Cat. No.98CH36207).

[8]  Rama Chellappa,et al.  A robust algorithm for fusing noisy depth estimates using stochastic approximation , 2001, 2001 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings (Cat. No.01CH37221).

[9]  Lennart Ljung,et al.  Theory and Practice of Recursive Identification , 1983 .

[10]  John Oliensis,et al.  Dealing with Noise in Multiframe Structure from Motion , 1999, Comput. Vis. Image Underst..

[11]  Carlo Tomasi,et al.  Good features to track , 1994, 1994 Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.

[12]  P. Kumar,et al.  Theory and practice of recursive identification , 1985, IEEE Transactions on Automatic Control.

[13]  W. Rudin.  Principles of mathematical analysis , 1964 .

[14]  Joseph A. O'Sullivan,et al.  Information-Theoretic Image Formation , 1998, IEEE Trans. Inf. Theory.