Analyzing Calibration Sensitivity in Markerless Tracking Systems

Motion capture (MOCAP) techniques based on markers have been used worldwide in the gait analysis field for years. Despite their accuracy, this is a costly method that needs specialized equipment and personnel. That is the reason why, nowadays, new low-cost methods such as markerless techniques based on human pose estimation (HPE) have been developed and progressively adopted for this purpose. The calibration stage in MOCAP systems is an important procedure that clearly impacts on the system performance. However, it is not fully validated how the results are affected by variations in the calibration procedures. This work proposes to evaluate two different spatial configurations of the acquisition devices modifying their height (H1, highest and H2, lowest) and different calibration procedures (intrinsics and extrinsics parameters) in a markerless system based on four smartphones iPhone SE. To evaluate the impact of intrinsics parameters, the distance between calibration pattern and camera (DPC); and the number of acquired frames (#frames) were modified. Three different calibration patterns (extrinsics calibration fitting) were evaluated to quantify the effect on markerless system performance. The final results of the trajectory of the markers were compared to the gold standard method, eight VICON Bonita cameras, data which was captured simultaneously. Comparisons were realized considering two metrics widely used in bibliography (MPJPE and PCK). The results show that H1 configuration performs slightly better than H2. Regarding extrinsic calibration, patterns that consider a volume more than a surface are better for both configurations. About the intrinsic calibration, the best performance is given by the minimum DPC with Pattern 2, with a negligible influence of #frames. Respecting PCK performance for different thresholds, the results are worse for H2 than for H1 in most of the markers. Comparing both methods, the most affected direction is the transversal while the vertical and anteroposterior show similar performances.