Physically based and probabilistic models for computer vision

Models of 2-D and 3-D objects are an essential aspect of computer vision. Physically-based models represent object shape and motion through dynamic differential equations and provide mechanisms for fitting and tracking visual data using simulated forces. Probabilistic models allow the incorporation of prior knowledge about shape and the optimal extraction of information from noisy sensory measurements. In this paper we propose a framework for combining the essential elements of both the physically-based and probabilistic approaches. The combined model is a Kalman filter which incorporates physically-based models as part of the prior and system dynamics and is able to integrate noisy data over time. In particular, through a suitable choice of parameters models can be built which either return to a rest shape when external data are removed or remember shape cues seen previously. The proposed framework shows promise in a number of computer vision applications.

[1]  Paul L. Meyer,et al.  Introductory Probability and Statistical Applications , 1970 .

[2]  B. Brown.  Proceedings of the Society of Photo-optical Instrumentation Engineers , 1975 .

[3]  A.H. Haddad,et al.  Applied optimal estimation , 1976, Proceedings of the IEEE.

[4]  Edward L. Wilson,et al.  Numerical methods in finite element analysis , 1976 .

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

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

[7]  Alex Pentland,et al.  Fractal-Based Description of Natural Scenes , 1984, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[8]  Demetri Terzopoulos,et al.  Regularization of Inverse Visual Problems Involving Discontinuities , 1986, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[9]  Hugh F. Durrant-Whyte,et al.  Consistent Integration and Propagation of Disparate Sensor Observations , 1986, Proceedings. 1986 IEEE International Conference on Robotics and Automation.

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

[11]  H. F. Durrant-White.  Consistent integration and propagation of disparate sensor observations , 1987 .

[12]  Richard Durbin,et al.  An analogue approach to the travelling salesman problem using an elastic net method , 1987, Nature.

[13]  Richard Szeliski,et al.  Regularization Uses Fractal Priors , 1987, AAAI.

[14]  Demetri Terzopoulos,et al.  The Computation of Visible-Surface Representations , 1988, IEEE Trans. Pattern Anal. Mach. Intell..

[15]  Richard Szeliski,et al.  An Analysis of the Elastic Net Approach to the Traveling Salesman Problem , 1989, Neural Computation.

[16]  Richard Szeliski,et al.  From splines to fractals , 1989, SIGGRAPH '89.

[17]  Dimitris N. Metaxas,et al.  Dynamic 3D models with local and global deformations: deformable superquadrics , 1990, [1990] Proceedings Third International Conference on Computer Vision.

[18]  Demetri Terzopoulos,et al.  Reconstructing and visualizing models of neuronal dendrites , 1991 .

[19]  Dimitris N. Metaxas,et al.  Constrained deformable superquadrics and nonrigid motion tracking , 1991, Proceedings. 1991 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[20]  Richard Szeliski,et al.  Shape from rotation , 1991, Proceedings. 1991 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[21]  Baba C. Vemuri,et al.  Geometric Methods in Computer Vision , 1991 .

[22]  Demetri Terzopoulos,et al.  Sampling and reconstruction with adaptive meshes , 1991, Proceedings. 1991 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[23]  Alex Pentland,et al.  Recovery of non-rigid motion and structure , 1991, Proceedings. 1991 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.