Stereo Vision Pose Estimation for Moving Objects by the Interacting Multiple Model Method

The stereo vision measurement system is very widely employed to obtain the 6 DOF pose information for the moving objects in space. However, the linear and angular velocities are impossible to estimate using these systems while the dynamic model is unknown and disturbances exist, and their applications is limited. To overcome this disadvantage, we propose an approach based on the IMM algorithm for moving objects. Our approach is verified in the feature points of a moving object. And the simulating results show its validity.