Relative position estimation between body segments is one essential process for inertial sensor-based human motion analysis. Conventionally, the relative position was calculated through a constant segment to joint (S2J) vector and the orientation of the segment, assuming that the segment was rigid. However, the S2J vector is deformed by soft tissue artifact (STA) of the segment. In a previous study, in order to handle the above problem, Lee and Lee proposed the relative position estimation method using time-varying S2J vectors based on inertial sensor signals. Here, time-varying S2J vectors were determined through the joint flexion angle using regression. However, it was not appropriate to consider only the flexion angle as a deformation-related variable. In addition, regression has limitations in considering complex joint motion. This paper proposed artificial neural network models to compensate for the STA by considering all three-axis motion of the joint. A verification test was conducted for lower body segments. Experimental results showed that the proposed method was superior to the previous method. For pelvis-to-foot relative position estimation, averaged root mean squared error of the previous method was 17.38 mm, while that of the proposed method was 12.71 mm.

Estimation of the relative position between the body segments is an important task in inertial sensor-based human motion tracking. Conventionally, the relative position is determined using orientations and constant segment vectors that connect from segment to joint center, based on the assumption that the segments are rigid. However, the human body segments are non-rigid, which leads to an inaccurate relative position estimation. This paper proposes a relative position estimation method based on inertial sensor signals, considering the non-rigidity of the human bodies. Considering that the effects of non-rigidity are highly correlated with a specific variable, the proposed method uses time-varying segment vectors determined by the specific physical variable, instead of using constant segment vectors. Verification test results for an upper-body model demonstrates the superiority of the proposed method over the conventional method: The averaged root mean square error of the sternum-to-forearm estimation from the conventional method was 34.19 ㎜, while the value from the proposed method was 16.67 ㎜.