Torque-based recursive filtering approach to the recovery of 3D articulated motion from image sequences

In this paper we introduce a recursive filtering method to recover the 3D articulated motion from image sequences. In recursive filtering frameworks, the quality of the results heavily depends on the choice of state variables and the determination of the process model; which models a real object whose motion is to be estimated. Our approach employs robotics dynamics into the recursive filtering framework. And the key strategy is to incorporate joint torques into the model state variables. In addition, we assumed the variations of the joint torques are Gaussian noises. We describe how to integrate dynamics equations into Kalman filters, and with the experimental results our method is shown to be effective.