Automated Analysis of the Origin of Movement: An Approach Based on Cooperative Games on Graphs

Abstract

In this work, a computational method is proposed to automatically investigate the perception of the origin of full-body human movement and its propagation. The method is based on a mathematical game built over a suitably defined graph structure representing the human body. The players of this game are the graph vertices, which form a subset of body joints. Since each vertex contributes to a shared goal (i.e., to the way in which a specific movement-related feature is transferred among the joints), a cooperative game-theoretical model (specifically a transferableutility game) is adopted, which is able (via the Shapley value) to measure the relevance of the various joints in human movement when performing full-body movement analysis. The method is theoretically investigated and applied to a motion capture dataset obtained from subjects who performed expressive movements. Finally, the method is validated through an online survey, in which several dancers/nondancers participated. The results show the capability of the proposed approach to represent the evolution of the most important joint responsible for originating each dancer's movement. Index Terms-Automated analysis of the perception of the origin of movement, cooperative game theory, full-body movement analysis, graph theory, transferable-utility (TU) games. PDGP 2018/20 DIT.AD016.001 (Technologies for Smart Communities). This article was recommended by Associate Editor X. Hu.

Implementation of a Human Motion Capture System Based on the Internet of Things Machine Vision

“…Classical mean square similarity error measurement functions include the maximum mean square cross-correlation measurement function (MR), the minimum maximum mean square level error measurement function (mse), and the minimum mean square average absolute value error and real value measurement function (MAD), etc. (Cui, 2020;Kolykhalova, 2020). (3) Optimal search of various transform space parameters.…”

On Braess’ Paradox and Average Quality of Service in Transportation Network Cooperative Games

“…It represents the average marginal contribution of each player across all possible coalitions, according to a suitable probability distribution (i.e., when players, starting from the empty coalition, enter the grand coalition randomly, in such a way that all orders are equally likely). It is worth noting that, due to the interpretation above, the Shapley value can be applied as a measure of players' importance not only in classical contexts in which the players are modeled as rational decision makers, but also in other more general situations in which this does not occur, e.g., when players are features in supervised machine learning problems [2], genes in microarray games [13], or joints in the analysis of motion capture datasets [10].…”