On a Dissimilarity Metric for Analyzing Body Synergistic Coordination in Non-Periodic Motion
Shunpei Fujii, Kanta Tachibana
TL;DR
Addresses measuring synergistic coordination between body segments in aperiodic motions (e.g., baseball pitching) by overcoming DTW's temporal warping and joint-wise similarity limitations. Proposes a convolution-based dissimilarity metric grounded in Linear Time-Invariant dynamics, using transfer functions $G_1(z)=\frac{B(z)}{A(z)}$ and $G_2(z)=\frac{Y(z)}{X(z)}$ and convolution descriptors $u=(a*y)$, $v=(x*b)$ with $\mathrm{Dis}((a,b),(x,y))=\frac{||u-v||^2}{||u||\,||v||}$. Empirically evaluated on six pitching videos and camera-angle perturbations, the method distinguishes same-pitcher from different-pitcher motions and remains robust to viewing angle and scale, outperforming DTW and some deep-learning baselines. The approach offers a principled, rhythm-aware tool for assessing inter-segment coordination with potential applications in sports analytics, rehabilitation, and robotics.
Abstract
This study proposes a novel metric to quantitatively evaluate body synergistic coordination, explicitly addressing dynamic interactions between pairs of body segments in baseball pitching motions. Conventional methods typically compare motion trajectories using individual joint coordinates or velocities independently, employing techniques like Dynamic Time Warping (DTW) that inherently apply temporal alignment even when such correction may distort meaningful rhythm-based differences. In contrast, our approach models the coordination dynamics as Linear Time-Invariant (LTI) systems, leveraging convolution operations between pairs of time series data to capture the gain and phase-lag inherent in genuine coordination dynamics. Empirical validation demonstrates the robustness of the proposed metric to variations in camera angles and scaling, providing superior discriminative capability compared to DTW and deep learning-based methods.