With the development of measurement technology, data on the movements of actual games in various sports can be obtained and used for planning and evaluating the tactics and strategy. Defense in team sports is generally difficult to be evaluated because of the lack of statistical data. Conventional evaluation methods based on predictions of scores are considered unreliable because they predict rare events throughout the game. Besides, it is difficult to evaluate various plays leading up to a score. In this study, we propose a method to evaluate team defense from a comprehensive perspective related to team performance by predicting ball recovery and being attacked, which occur more frequently than goals, using player actions and positional data of all players and the ball. Using data from 45 soccer matches, we examined the relationship between the proposed index and team performance in actual matches and throughout a season. Results show that the proposed classifiers predicted the true events (mean F1 score > 0.483) better than the existing classifiers which were based on rare events or goals (mean F1 score < 0.201). Also, the proposed index had a moderate correlation with the long-term outcomes of the season (r= 0.397). These results suggest that the proposed index might be a more reliable indicator rather than winning or losing with the inclusion of accidental factors.

Tracking devices that can track both players and balls are critical to the performance of sports teams. Recently, significant effort has been focused on building larger broadcast sports video datasets. However, broadcast videos do not show the entire pitch and only provides partial information about the game. On the other hand, other camera perspectives can capture the whole field in a single frame, such as fish-eye and bird-eye view (drone) cameras. Unfortunately, there has not been a dataset where such data has been publicly shared until now. This paper proposes SoccerTrack, a dataset set consisting of GNSS and bounding box tracking data annotated on video captured with a 8K-resolution fish-eye camera and a 4K-resolution drone camera. In addition to a benchmark tracking algorithm, we include code for camera calibration and other preprocessing. Finally, we evaluate the tracking accuracy among a GNSS, fish-eye camera and drone camera data. SoccerTrack is expected to provide a more robust foundation for designing MOT algorithms that are less reliant on visual cues and more reliant on motion analysis. The dataset and related project code is available at https://github.com/AtomScott/SoccerTrack¹².

Groups of social organisms in nature are resilient systems that can overcome unpredicted threats by helping its members. These social organisms are assumed to behave both autonomously and cooperatively as individuals, the helper, the helped and other part of a group depending on the context such as emergencies. However, the structure and function of these resilient actions, such as how helpers help colleagues and how the helper’s action is effective at multiple subsystem scales remain unclear. Here we investigated the behaviour of organised and efficient small human groups in a ballgame defence, and identified three principles of hierarchical resilient help when under attack. First, at a present high emergency level, the helper simply switched the local roles in the attacked subsystem with the helped. Second, at an intermediate emergency level, the helpers effectively acted in overlapping subsystems. Third, for the most critical emergency, the helpers globally switched the action on the overall system. These resilient actions to the benefit of the system were assumed to be observed in only humans, which help colleagues at flexibly switched and overlapped hierarchical subsystem. We suggest that these multi-layered helping behaviours can help to understand resilient cooperation in social organisms and human groups.

Modeling the complex collective behavior is a challenging issue in several material and life sciences. The collective motion has been usually modeled by simple interaction rules and explained by global statistics. However, it remains difficult to bridge the gap between the dynamic properties of the complex interaction and the emerging group-level functions. Here we introduce decomposition methods to directly extract and classify the latent global dynamics of nonlinear dynamical systems in an equation-free manner, even including complex interaction in few data dimensions. We first verified that the basic decomposition method can extract and discriminate the dynamics of a well-known rule-based fish-schooling (or bird-flocking) model. The method extracted different temporal frequency modes with spatial interaction coherence among three distinct emergent motions, whereas these wave properties in multiple spatiotemporal scales showed similar dispersion relations. Second, we extended the basic method to map high-dimensional feature space for application to actual small-dimensional systems complexly changing the interaction rules. Using group sports human data, we classified the dynamics and predicted the group objective achievement. Our methods have a potential for classifying collective motions in various domains which obey in non-trivial dominance law known as active matters. Modeling complex collective motions is a challenging problem such as in biology, physics, and human behavior because the rules governing the motion are sometimes unclear. Then, researchers have usually used simple interaction model and explain global statistics. However, it remains difficult to bridge the gap between the dynamic properties of the complex interaction and the group-level functions. This study develops an effective framework to extract the dynamics of collective motion from data by data-driven modeling. Compared with conventional methods, our method can be applied to cases with the small numbers of group members or transient and complex changes of the behavioral rules. Our methods successfully discriminated group movements of well-known fish-schooling models and predicted the achievement of a group objective from actual basketball players’ position data. Our methods have a potential for outcome prediction and classification for various unsolved and complex collective motions such as in biology and physics.

Analysis of invasive sports such as soccer is challenging because the game situation changes continuously in time and space, and multiple agents individually recognize the game situation and make decisions. Previous studies using deep reinforcement learning have often considered teams as a single agent and valued the teams and players who hold the ball in each discrete event. Then it was challenging to value the actions of multiple players, including players far from the ball, in a spatiotemporally continuous state space. In this paper, we propose a method of valuing possible actions for on- and off-ball soccer players in a single holistic framework based on multi-agent deep reinforcement learning. We consider a discrete action space in each data frame that mimics that of Google research football and leverages supervised learning for actions in reinforcement learning. In the experiment, we analyzed the relationships with conventional indicators, season goals, and game ratings by experts, and showed the effectiveness of the proposed method. Our approach can assess how multiple players move continuously throughout the game, which is difficult to be discretized or labeled but vital for teamwork, scouting, and fan engagement.