In this experiment we have verified, whether tracking can be carried out in the wavelet subspace. This subspace method is an enhancement of the approach in [Krüger and Sommer, 2000]. First, we have optimized a WN on the face image that we want to track, where . This WN will serve as our face template. Using eq. (4) and the notation of eq. (1), we can deform the template WN affinely:
Tracking is established by finding at each time step the appropriate deformation parameters of the superwavelet such that the sum-of-squared difference between the image at time and the deformed template is minimized. To do so, we project at each time step the image into the wavelet subspace. This was done by first setting , and of the superwavelet in eq. (11) to roughly appropriate values (e.g. by using the computed deformation values from the previous time step) and by then using the deformed dual wavelets to compute the corresponding wavelet coefficients . The difference
Estimating the optimal deformation values can be done efficiently: Since the linear combination of the wavelets is a wavelet, from above is again a wavelet and the optimization scheme of Section 2 can be applied. The employed Levenberg-Marquardt algorithm needs a number of cycles in which the deformation parameters are refined until a certain optimum is reached. In each cycle in eq. (13) has to be recomputed. For a WN with 16 wavelets, this, however, needs just 16 projections of the filters onto the image. Since it can be shown that the matrix in eq. (7) is invariant (except some factor) to the changes due to , and , it needs to be computed only once at the beginning. With a WN with wavelets we have reached 30 fps on a 700 MHz Linux-Pentium. Because of the high frame rate, the differences between successive images were small and the Levenberg-Marquardt algorithm seldomly exceeded 7 cycles. An example can be seen in fig. 5. The white box indicates the tracked inner-face region, on which our template WN was optimized. We have also experimented with different number of wavelets and noticed a linear decrease in speed, but an increase in precision for larger (). A more detailed description of our experimental results can be found in [Feris et al., 2001].
|