3D pose estimation via elliptical fourier descriptors for deformable hand representations

Pose and Gesture tracking is a sensitive procedure in different computer vision applications. One of the problems concerning Sign Language recognition is that the 3-D trajectory and the orientation could not be carefully detected. This paper analyses the aforementioned problem from a sequence of stereo images. In this paper, we present an effective algorithm for the estimation of the 3-D trajectory and orientation of a signer's hand. The so-called algorithm utilizes two different procedures in order to extract the 3-D motion model Point Correspondence and 3-D motion estimation. Many papers which deal with this kind of problem assume that an accurate match between the feature points has been made, and so, deal with only the 3-D motion estimation problem. The registration of the feature points are done by means of Elliptical Fourier representations of a closed curve. After the registrations of feature points are completed, the hand's 3-D trajectory and orientation could be easily computed using a single-stage linear method. This method is applied to both synthetic and real image sequences and the results are shown.