Motion-Model-Based Boundary Extraction and a Real-Time Implementation

Motion boundary extraction and optical flow computation are two subproblems of the motion recovery problem that cannot be solved independently of one another. These two problems have been treated separately. A popular recent approach uses an iterative scheme that consists of motion boundary extraction and optical flow computation components and refines each result through iteration. We present a local, noniterative algorithm that simultaneously extracts motion boundaries and computes optical flow. This is achieved by modeling 3-D Hermite polynomial decompositions of image sequences representing the perspective projection of 3-D general motion. Local model parameters are used to determine whether motion should be estimated or motion boundaries should be extracted at the neighborhood. A definite advantage of this noniterative algorithm is its efficiency. It is demonstrated by a real-time implementation and supporting experimental results.

[1]  Kim L. Boyer,et al.  On Optimal Infinite Impulse Response Edge Detection Filters , 1991, IEEE Trans. Pattern Anal. Mach. Intell..

[2]  F. Heyden.  Evaluation of edge detection algorithms , 1989 .

[3]  Kenji Mase,et al.  Unified computational theory for motion transparency and motion boundaries based on eigenenergy analysis , 1991, Proceedings. 1991 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[4]  Jack Sklansky,et al.  Multiple-order derivatives for detecting local image characteristics , 1987 .

[5]  A. Pentland,et al.  Robust estimation of a multi-layered motion representation , 1991, Proceedings of the IEEE Workshop on Visual Motion.

[6]  David W. Murray,et al.  Scene Segmentation from Visual Motion Using Global Optimization , 1987, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[7]  Michael J. Black,et al.  Mixture models for optical flow computation , 1993, Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.

[8]  David W. Murray,et al.  Detecting the image boundaries between optical flow fields from several moving planar facets , 1986, Pattern Recognit. Lett..

[9]  Michael J. Black,et al.  The Robust Estimation of Multiple Motions: Parametric and Piecewise-Smooth Flow Fields , 1996, Comput. Vis. Image Underst..

[10]  Joachim Dengler.  Estimation of Discontinuous Displacement Vector Fields with the Minimum Description Length Criterion , 1991, DAGM-Symposium.

[11]  Tomaso A. Poggio,et al.  Motion Field and Optical Flow: Qualitative Properties , 1989, IEEE Trans. Pattern Anal. Mach. Intell..

[12]  O. Braddick.  A short-range process in apparent motion. , 1974, Vision research.

[13]  Berthold K. P. Horn,et al.  Determining Optical Flow , 1981, Other Conferences.

[14]  I.E. Abdou,et al.  Quantitative design and evaluation of enhancement/thresholding edge detectors , 1979, Proceedings of the IEEE.

[15]  Larry S. Davis,et al.  Contour-based motion estimation , 1982, Comput. Vis. Graph. Image Process..

[16]  John F. Canny,et al.  A Computational Approach to Edge Detection , 1986, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[17]  Narendra Ahuja,et al.  Motion and Structure Factorization and Segmentation of Long Multiple Motion Image Sequences , 1992, ECCV.

[18]  Richard A. Young,et al.  SIMULATION OF HUMAN RETINAL FUNCTION WITH THE GAUSSIAN DERIVATIVE MODEL. , 1986 .

[19]  Gilad Adiv,et al.  Inherent Ambiguities in Recovering 3-D Motion and Structure from a Noisy Flow Field , 1989, IEEE Trans. Pattern Anal. Mach. Intell..

[20]  Eric Dubois,et al.  Bayesian Estimation of Motion Vector Fields , 1992, IEEE Trans. Pattern Anal. Mach. Intell..

[21]  William B. Thompson,et al.  Analysis of Accretion and Deletion at Boundaries in Dynamic Scenes , 1984, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[22]  Yiannis Aloimonos,et al.  Obstacle Avoidance Using Flow Field Divergence , 1989, IEEE Trans. Pattern Anal. Mach. Intell..

[23]  Patrick Bouthemy,et al.  A Maximum Likelihood Framework for Determining Moving Edges , 1989, IEEE Trans. Pattern Anal. Mach. Intell..

[24]  C Koch,et al.  Analog "neuronal" networks in early vision. , 1986, Proceedings of the National Academy of Sciences of the United States of America.

[25]  Jerry L. Potter,et al.  Velocity as a Cue to Segmentation , 1975, IEEE Transactions on Systems, Man, and Cybernetics.

[26]  Patrick Bouthemy,et al.  Multimodal Estimation of Discontinuous Optical Flow using Markov Random Fields , 1993, IEEE Trans. Pattern Anal. Mach. Intell..

[27]  Hongche Liu.  A general motion model and spatio-temporal filters for 3-D motion interpretations , 1995 .

[28]  K. Nakayama,et al.  Optical Velocity Patterns, Velocity-Sensitive Neurons, and Space Perception: A Hypothesis , 1974, Perception.

[29]  Joseph K. Kearney,et al.  Optical Flow Estimation: An Error Analysis of Gradient-Based Methods with Local Optimization , 1987, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[30]  Rama Chellappa,et al.  A generalized motion model for estimating optical flow using 3-D Hermite polynomials , 1994, Proceedings of 12th International Conference on Pattern Recognition.

[31]  Valdis Berzins,et al.  Dynamic Occlusion Analysis in Optical Flow Fields , 1985, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[32]  A. Yuille,et al.  A model for the estimate of local image velocity by cells in the visual cortex , 1990, Proceedings of the Royal Society of London. B. Biological Sciences.

[33]  Ralph Hartley,et al.  Segmentation of optical flow fields by pyramid linking , 1985, Pattern Recognit. Lett..

[34]  Brian G. Schunck,et al.  Image Flow Segmentation and Estimation by Constraint Line Clustering , 1989, IEEE Trans. Pattern Anal. Mach. Intell..

[35]  Shmuel Peleg,et al.  A Three-Frame Algorithm for Estimating Two-Component Image Motion , 1992, IEEE Trans. Pattern Anal. Mach. Intell..