A feature based method for tracking the 3-D trajectory and the orientation of a signer’s hand

Pose 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 using a single camera. This paper analyses the aforementioned problem from a sequence of stereo images. In this paper, we present a fast and effective algorithm for the estimation of the 3-D trajectory and orientation of a signerpsilas hand. The so-called algorithm utilizes two different procedures in order to extract the 3-D motion model, the registration step and the motion estimation step using limited feature points. Many papers which deal with this kind of problem assume that an accurate match between the corresponding points have been made, and so, deal with only the 3-D motion estimation problem. In our approach, we tackle the registration procedure with two different registration techniques. The registration of the right and left image sequences are done by means of a simple but effective technique but the registration of the feature points in two different frames are done using a more complex correlation based routine. After the registrations of feature points are completed, the handpsilas 3-D trajectory and orientation could be easily computed. This method is applied to both synthetic and real image sequences and the results obtained utilizing our method confirms this approach.