论文信息 - Vector Fields Modelization Using Basis of Polynomials: Application to the Analysis of Simple Face Movements

Vector Fields Modelization Using Basis of Polynomials: Application to the Analysis of Simple Face Movements

In this communication we present an original and general model for the approximation of vector fields and especially displacement vector fields. The proposed method uses the orthonormal multivariate polynomials framework to approximate vector fields as combinations of these particular functions. Then we demonstrate the noise robustness of our model. And finally we show that the model can efficiently be used for the recognition of simple face movement in a Webcam acquired sequence

Martin Druon | Benoit Tremblais | Bertrand Augereau

[1] David J. Fleet,et al. Performance of optical flow techniques , 1994, International Journal of Computer Vision.

[2] Yuan Xu,et al. Orthogonal Polynomials of Several Variables , 2014, 1701.02709.

[3] Yuan Xu,et al. Orthogonal Polynomials of Several Variables: Preface , 2001 .

[4] Takeo Kanade,et al. An Iterative Image Registration Technique with an Application to Stereo Vision , 1981, IJCAI.

[5] Berthold K. P. Horn,et al. Determining Optical Flow , 1981, Other Conferences.

[6] Pierre Kornprobst,et al. A Course to Fine Multiscale Approach for Linear Least Squares Optical Flow Estimation , 2004, BMVC.

[7] P. Kornprobst,et al. A Coarse To Fine Multiscale Approach For Linear Least Squares Optical Flow Estimation , 2000 .

[8] Christine Fernandez-Maloigne,et al. Vectorial Computation of the Optical Flow in Color Image Sequences , 2005, Color Imaging Conference.

[9] Mubarak Shah,et al. Motion-based recognition a survey , 1995, Image Vis. Comput..

[10] Yuan Xu,et al. Orthogonal Polynomials of Several Variables: Subject index , 2001 .

[11] Hanno Scharr,et al. Accurate optical flow in noisy image sequences using flow adapted anisotropic diffusion , 2005, Signal Process. Image Commun..