Temporally integrated surface reconstruction

A solution is presented to the problem of obtaining and improving an estimate of the 3-D structure of a scene from a sequence of images. The algorithm, which combines single-frame reconstruction techniques and multiple-frame Kalman filtering, is tested on a variety of real motion image sequences.<<ETX>>

[1]  Demetri Terzopoulos,et al.  Multilevel computational processes for visual surface reconstruction , 1983, Comput. Vis. Graph. Image Process..

[2]  Donald Geman,et al.  Stochastic Relaxation, Gibbs Distributions, and the Bayesian Restoration of Images , 1984, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[3]  Berthold K. P. Horn.  Robot vision , 1986, MIT electrical engineering and computer science series.

[4]  Andrew Blake,et al.  Visual Reconstruction , 1987, Deep Learning for EEG-Based Brain–Computer Interfaces.

[5]  R. Szeliski,et al.  Incremental estimation of dense depth maps from image sequences , 1988, Proceedings CVPR '88: The Computer Society Conference on Computer Vision and Pattern Recognition.

[6]  Joachim Heel,et al.  Dynamic Motion Vision , 1989, Other Conferences.