Motion estimation using the spatio-temporal continuous wavelet transform: new results and alternative implementations

The spatio-temporal continuous wavelet transform (CWT) has proven useful for motion estimation (Me) applications. We present tracking results that highlight the ability of the CWT approach to handle non-linear motion and time-varying object signatures (as those produced by 3D motion projected in the image plane). In addition, we present two low-complexity approaches that emulate the behavior of the CWT velocity selective filters. The first approach is based on infinity impulse response (IIR) approximations of the temporal response of the CWT filters. The second technique is based on directional decompositions and results in a novel 3D decomposition, the directional filter bank.

[1]  Mark J. T. Smith,et al.  Robust object tracking in compressed image sequences , 1998, J. Electronic Imaging.

[2]  Fernando Alberto Mujica.  Spatio-temporal continuous wavelet transform for motion estimation , 1999 .

[3]  Mark J. T. Smith,et al.  A new directional filter bank for image analysis and classification , 1999, 1999 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings. ICASSP99 (Cat. No.99CH36258).

[4]  Mark J. T. Smith,et al.  A new motion parameter estimation algorithm based on the continuous wavelet transform , 2000, IEEE Trans. Image Process..

[5]  Thomas S. Huang,et al.  Image sequence analysis , 1981 .

[6]  R.M. Gagliardi,et al.  Application of Three-Dimensional Filtering to Moving Target Detection , 1983, IEEE Transactions on Aerospace and Electronic Systems.