An Adaptive Multiscale Scheme for Real-Time Motion Field Estimation

The problem considered in this work is that of estimating the motion field (i.e. the projection of the velocity field onto the image plane) from a temporal sequence of images. Generic images contain different objects with diverse spatial frequencies and motion amplitudes. To deal with this complex environment in a fast and effective way, biological visual systems use parallel processing, visual channels at different resolutions and adaptive mechanisms. In this paper a new adaptive multiscale scheme is proposed, in which the spatial discretization scale is based on a local estimate of the errors involved. Considering the constraints for real-time operation, flexibility and portability, the scheme can be implemented on MIMD parallel computers with medium size grains with high efficiency. Tests with ray-traced and video-acquired images for different motion ranges show that this method produces a better estimation with respect to the homogeneous (no Gadap t ive) mult iscale met hod.

[1]  Dirk Roose,et al.  Benchmarking the iPSC/2 Hypercube Multiprocessor , 1989, Concurr. Pract. Exp..

[2]  F. Glazer.  Multilevel Relaxation in Low-Level Computer Vision , 1984 .

[3]  P. J. Burt,et al.  The Pyramid as a Structure for Efficient Computation , 1984 .

[4]  Leonard Uhr,et al.  Parallel computer vision , 1987 .

[5]  Demetri Terzopoulos,et al.  Image Analysis Using Multigrid Relaxation Methods , 1986, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[6]  Quentin F. Stout,et al.  Supporting Divide-and-Conquer Algorithms for Image Processing , 1987, J. Parallel Distributed Comput..

[7]  R. Battiti,et al.  Surface Reconstruction and Discontinuity Detection: A Fast Hierarchical Approach on a Two-Dimensional Mesh , 1990, Proceedings of the Fifth Distributed Memory Computing Conference, 1990..

[8]  Yousef Saad,et al.  Multigrid Algorithms on the Hypercube Multiprocessor , 1986, IEEE Transactions on Computers.

[9]  Karl SOLCHENBACH.  Grid applications on distributed memory architectures: Implementation and evaluation , 1988, Parallel Comput..

[10]  Tomaso Poggio,et al.  Computational vision and regularization theory , 1985, Nature.

[11]  G. Wasilkowski,et al.  Computing optical flow , 1989, [1989] Proceedings. Workshop on Visual Motion.

[12]  John R. Kender,et al.  Low-Level Image Analysis Tasks on Fine-Grained Tree-Structured SIMD Machines , 1987, J. Parallel Distributed Comput..

[13]  Dirk Roose,et al.  Efficiency and load balancing issues for a parallel component labelling algorithm , 1989 .

[14]  D. Brandt,et al.  Multi-level adaptive solutions to boundary-value problems math comptr , 1977 .

[15]  Oliver A. McBryan,et al.  Hypercube Algorithms and Implementations , 1985, PPSC.

[16]  G. C. Fox,et al.  Integrated Vision Project on the Computer Network , 1988 .

[17]  Wilfried Enkelmann,et al.  Investigations of multigrid algorithms for the estimation of optical flow fields in image sequences , 1988, Comput. Vis. Graph. Image Process..