Motion feature detection using steerable flow fields

The estimation and detection of occlusion boundaries and moving bars are important and challenging problems in image sequence analysis. Here, we model such motion features as linear combinations of steerable basis flow fields. These models constrain the interpretation of image motion, and are used in the same way as translational or affine motion models. We estimate the subspace coefficients of the motion feature models directly from spatiotemporal image derivatives using a robust regression method. From the subspace coefficients we detect the presence of a motion feature and solve for the orientation of the feature and the relative velocities of the surfaces. Our method does not require the prior computation of optical flow and recovers accurate estimates of orientation and velocity.

[1]  J. Potter.  Scene segmentation using motion information , 1977 .

[2]  Anselm Spoerri,et al.  The early detection of motion boundaries , 1990, ICCV 1987.

[3]  Michael J. Black,et al.  Constraints for the Early Detection of Discontinuity from Motion , 1990, AAAI.

[4]  Edward H. Adelson,et al.  The Design and Use of Steerable Filters , 1991, IEEE Trans. Pattern Anal. Mach. Intell..

[5]  P. Anandan,et al.  Hierarchical Model-Based Motion Estimation , 1992, ECCV.

[6]  Keith Langley,et al.  Computational analysis of non-Fourier motion , 1994, Vision Research.

[7]  Deformable Kernels for Early Vision , 1995, IEEE Trans. Pattern Anal. Mach. Intell..

[8]  Sourabh A. Niyogi,et al.  Detecting kinetic occlusion , 1995, Proceedings of IEEE International Conference on Computer Vision.

[9]  Stephen M. Omohundro,et al.  Nonlinear manifold learning for visual speech recognition , 1995, Proceedings of IEEE International Conference on Computer Vision.

[10]  George T. Chou,et al.  A model of figure-ground segregation from kinetic occlusion , 1995, Proceedings of IEEE International Conference on Computer Vision.

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

[12]  David J. Fleet,et al.  Learning parameterized models of image motion , 1997, Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.