On Transparent Motion Computation

We extend the principle of phase-based techniques for measuring optical flow and binocular disparity to multiple motion estimation. We analyse multiple optical flows by estimating phase gradients (instantaneous frequencies) from a set of independent bandpass quadrature filter pairs. Our approach is similar to that of Shizawa and Mase [22], in which nth-order differential operators are required to compute n simultaneous velocity estimates. The approach presented here only requires a set of band-pass niters and their first derivatives.

[1]  A. Papoulis.  Systems and transforms with applications in optics , 1981 .

[2]  David J. Fleet,et al.  Computation of normal velocity from local phase information , 1989, Proceedings CVPR '89: IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[3]  David J. Fleet,et al.  Stability of Phase Information , 1993, IEEE Trans. Pattern Anal. Mach. Intell..

[4]  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.

[5]  R.N. Bracewell,et al.  Signal analysis , 1978, Proceedings of the IEEE.

[6]  Azriel Rosenfeld,et al.  The perception of visual motion coherence and transparency: a statistical model , 1991, Proceedings IROS '91:IEEE/RSJ International Workshop on Intelligent Robots and Systems '91.

[7]  K Langley.  Using group and phase velocity to explain coherent and transparent motion , 1992 .

[8]  M. Shizawa,et al.  Principle of superposition: a common computational framework for analysis of multiple motion , 1991, Proceedings of the IEEE Workshop on Visual Motion.

[9]  E H Adelson,et al.  Spatiotemporal energy models for the perception of motion. , 1985, Journal of the Optical Society of America. A, Optics and image science.

[10]  David J. Fleet,et al.  Scale-Space Singularities , 1990, ECCV.

[11]  Shmuel Peleg,et al.  Computing two motions from three frames , 1990, [1990] Proceedings Third International Conference on Computer Vision.

[12]  K. Langley,et al.  Vertical and Horizontal Disparities from Phase , 1990, ECCV.

[13]  G. Granlund,et al.  Estimation of velocity, acceleration and disparity in time sequences , 1991, Proceedings of the IEEE Workshop on Visual Motion.

[14]  D J Heeger,et al.  Model for the extraction of image flow. , 1987, Journal of the Optical Society of America. A, Optics and image science.