Kinematic evaluation of articulated rigid objects

This research is focused on providing solutions for kinematic evaluation of articulated rigid objects when noisy data is available. Recent results proposed different techniques which necessitate learning stages or large relative motions. Our approach starts from a complete analytical solution which uses only point and line features to parametrize the rigid motion. This analytical solution is built using orthogonal dual tensors generated by rigid basis of dual vectors. Next, the necessary transformations are added to the theoretical solution so it can be used with noisy data input. Thus, the computational procedure is revealed and different experiments are presented in order to underline the advantages of the proposed approach.