Forward Kinematic Based Approach Using Sensor Fusion for Tracking the Human Limb
Arthur T. Johnson, Aswin K Ramasubramanian, Robins Mathew, Brian Mulkeen, Nikolaos Papakostas · 2022 IEEE 28th International Conference on Engineering, Technology and Innovation (ICE/ITMC) & 31st International Association For Management of Technology (IAMOT) Joint Conference · 2022
A vision-inertial sensor fusion algorithm that utilises a vision system to calibrate a forward kinematic model of the arm, mounted with Inertial Measurement Units (IMU) is proposed. This model utilises the data from both IMU and vision system to track the position and orientation of the arm. The algorithm was initially tested for drift error whilst working only with the IMU. Further tests are carried out to verify the improvement using the new algorithm. The results are compared with body tracking data obtained from the vision system and a baseline measurement of points in the real world. The results show that the proposed algorithm improves the overall accuracy of the system whilst operating at a higher frequency matching the output of the IMU sensors.