Showing papers by "Martin Lames published in 2021"

Validation of Player and Ball Tracking with a Local Positioning System

Abstract: The aim of this study was the validation of player and ball position measurements of Kinexon's local positioning system (LPS) in handball and football. Eight athletes conducted a sport-specific course (SSC) and small sided football games (SSG), simultaneously tracked by the LPS and an infrared camera-based motion capture system as reference system. Furthermore, football shots and handball throws were performed to evaluate ball tracking. The position root mean square error (RMSE) for player tracking was 9 cm for SSCs, the instantaneous peak speed showed a percentage deviation from the reference system of 0.7-1.7% for different exercises. The RMSE for SSGs was 8 cm. Covered distance was overestimated by 0.6% in SSCs and 1.0% in SSGs. The 2D RMSE of ball tracking was 15 cm in SSGs, 3D position errors of shot and throw impact locations were 17 cm and 21 cm. The methodology for the validation of a system's accuracy in sports tracking requires extensive attention, especially in settings covering both, player and ball measurements. Most tracking errors for player tracking were smaller or in line with errors found for comparable systems in the literature. Ball tracking showed a larger error than player tracking. Here, the influence of the positioning of the sensor must be further reviewed. In total, the accuracy of Kinexon's LPS has proven to represent the current state of the art for player and ball position detection in team sports.

State Transition Modeling in Ultimate Frisbee: Adaptation of a Promising Method for Performance Analysis in Invasion Sports.

Abstract: Although the body of literature in sport science is growing rapidly, certain sports have yet to benefit from this increased interest by the scientific community. One such sport is Ultimate Frisbee, officially known as Ultimate. Thus, the goal of this study was to describe the nature of the sport by identifying differences between winning and losing teams in elite-level competition. To do so, a customized observational system and a state transition model were developed and applied to 14 games from the 2017 American Ultimate Disc League season. The results reveal that, on average, 262.2 passes were completed by a team per game and 5.5 passes per possession. More than two-thirds of these passes were played from the mid zone (39.4 ± 6.57%) and the rear zone (35.2 ± 5.09%), nearest the team's own end zone. Winning and losing teams do not differ in these general patterns, but winning teams played significantly fewer backward passes from the front zone to the mid zone, nearest the opponent's end zone than losing teams (mean difference of -4.73%, t(13) = -4.980, p < 0.001, d = -1.16). Furthermore, losing teams scored fewer points when they started on defense, called breakpoints (mean difference of -5.57, t(13) = -6.365, p < 0.001, d = 2.30), and committed significantly more turnovers per game (mean difference of 5.64, t(13) = 5.85, p < 0.001, d = -1.18). Overall, this study provides the first empirical description of Ultimate and identifies relevant performance indicators to discriminate between winning and losing teams. We hope this article sheds light on the unique, but so far overlooked sport of Ultimate, and offers performance analysts the basis for future studies using state transition modeling in Ultimate as well as other invasion sports.

Bewegungszeit, Belastungsintensität und Bewegungsumfang im Sportunterricht - Schwerpunkt: Fußball

Abstract: Untersuchungen zu Bewegungsanteilen im Sportunterricht unter Verwendung objektiver Verfahren sind in Deutschland selten. Sie sind jedoch sowohl aus gesundheits- und trainingswissenschaftlicher als auch aus sportpadagogischer Perspektive von Interesse, um Schulsportwirklichkeit systematisch analysieren zu konnen. Der vorliegende Beitrag untersucht Bewegungszeit (Minuten), Belastungsintensitat (Herzschlage pro Minute) und Bewegungsumfang (Meter pro Minute) im Sportunterricht am Beispiel des Unterrichtsinhalts Fusball. Im Zentrum steht die Frage, ob sich Unterschiede fur die Unterrichtsdauer (Einzelstunde/Doppelstunde), das Setting (indoor/outdoor) und das Geschlecht zeigen. Insgesamt nahmen 356 Schuler*innen (247 mannlich, 109 weiblich) von der funften bis zur zehnten Jahrgangsstufe (MAlter = 12,4 Jahre) eines Gymnasiums in Bayern an der Untersuchung teil. Zum Einsatz kamen standardisierte Beobachtungsprotokolle, Herzfrequenzmesser und ein Trackingsystem (Local Position Measurement System [LPM-System]). Die Ergebnisse zeigten, dass die relative Bewegungszeit, die Belastungsintensitat und der Bewegungsumfang in Einzelstunden am hochsten waren. Die relative Bewegungszeit war outdoor etwas hoher als indoor. Die durchschnittliche Herzfrequenz unterschied sich nicht nach Setting und Geschlecht. Jungen erzielten einen hoheren durchschnittlichen Bewegungsumfang im Vergleich zu Madchen. Insgesamt deuten die Ergebnisse darauf hin, dass der Sportunterricht mit dem Inhalt Fusball einen substanziellen Beitrag zum taglichen Gesundheits- und Bewegungsverhalten leisten kann.

Design and Validation of an Observational System for Penalty Kick Analysis in Football (OSPAF).

Abstract: The analysis of penalty kick has played an important role in performance analysis. The study aims are to get formal feedback on the relevance of variables for penalty kick analysis, to design and validate an observational system; and to assess experts' opinion on the optimum video footage in penalty kick analysis. A structured development process was adopted for content validity, reliability and agreement on video usage. All observational variables included in OSPAF showed Aiken's V values above the cut-off (for 5-scale V> 0.64; for 2-scale = V > 0.75; p < 0.05). Cohen's Kappa resulted in mean intra- and inter-rater reliability values of 0.90 and 0.86, respectively. It is recommended to combine at least three different viewing angles (V = 0.90; p = 0.006) with standardization of video quality (V = 0.95; p = 0.006). Changing the viewing angles may influence the observer perception (V = 0.86; p = 0.006). The aerial and pitch-level viewing angle behind the penalty taker and pitch-level viewing angle behind the goalkeeper were indicated as most appropriate for observational analysis (V = 0.97; p = 0.01). The OSPAF met all requirements of instrument validation. It may be recommended as basis of future observational systems on penalty kicks.

Simulating Defensive Trajectories in American Football for Predicting League Average Defensive Movements.

Abstract: American football is an appealing field of research for the use of information technology. While much effort is made to analyze the offensive team in recent years, reasoning about defensive behavior is an emergent topic. As defensive performance and positioning largely contribute to the overall success of the whole team, this study introduces a method to simulate defensive trajectories. The simulation is evaluated by comparing the movements in individual plays to a simulated league average behavior. A data-driven ghosting approach is proposed. Deep neural networks are trained with a multi-agent imitation learning approach, using the tracking data of players of a whole National Football League (NFL) regular season. To evaluate the quality of the predicted movements, a formation-based pass completion probability model is introduced. With the implementation of a learnable order invariant model, based on insights of molecular dynamical machine learning, the accuracy of the model is increased to 81%. The trained pass completion probability model is used to evaluate the ghosted trajectories and serves as a metric to compare the true trajectory to the ghosted ones. Additionally, the study evaluates the ghosting approach with respect to different optimization methods and dataset augmentation. It is shown that a multi-agent imitation learning approach trained with a dataset aggregation method outperforms baseline approaches on the dataset. This network and evaluation scheme presents a new method for teams, sports analysts, and sports scientists to evaluate defensive plays in American football and lays the foundation for more sophisticated data-driven simulation methods.

Detection of Ground Contact Times with Inertial Sensors in Elite 100-m Sprints under Competitive Field Conditions

Abstract: This study describes a method for extracting the stride parameter ground contact time (GCT) from inertial sensor signals in sprinting. Five elite athletes were equipped with inertial measurement units (IMU) on their ankles and performed 34 maximum 50 and 100-m sprints. The GCT of each step was estimated based on features of the recorded IMU signals. Additionally, a photo-electric measurement system covered a 50-m corridor of the track to generate ground truth data. This corridor was placed interchangeably at the first and the last 50-ms of the track. In total, 863 of 889 steps (97.08%) were detected correctly. On average, ground truth data were underestimated by 3.55 ms. The root mean square error of GCT was 7.97 ms. Error analyses showed that GCT at the beginning and the end of the sprint was classified with smaller errors. For single runs the visualization of step-by-step GCT was demonstrated as a new diagnostic instrument for sprint running. The results show the high potential of IMUs to provide the temporal parameter GCT for elite-level athletes.

Assessment of Sprint Parameters in Top Speed Interval in 100 m Sprint-A Pilot Study Under Field Conditions.

Abstract: Improving performances in sprinting requires feedback on sprint parameters such as step length and step time. However, these parameters from the top speed interval (TSI) are difficult to collect in a competition setting. Recent advances in tracking technology allows to provide positional data with high spatio-temporal resolution. This pilot study, therefore, aims to automatically obtain general sprint parameters, parameters characterizing, and derived from TSI from raw speed. In addition, we propose a method for obtaining the intra-cyclic speed amplitude in TSI. We analyzed 32 100 m-sprints of 7 male and 9 female athletes (18.9 ± 2.8 years; 100 m PB 10.55-12.41 s, respectively, 12.18-13.31 s). Spatio-temporal data was collected with a radio-based position detection system (RedFIR, Fraunhofer Institute, Germany). A general velocity curve was fitted to the overall speed curve (vbase), TSI (upper quintile of vbase values) was determined and a cosine term was added to vbase within TSI (vcycle) to capture the cyclic nature of speed. This allowed to derive TSI parameters including TSI amplitude from the fitted parameters of the cosine term. Results showed good approximation for vbase (error: 5.0 ± 1.0%) and for vcycle (2.0 ± 1.0%). For validation we compared spatio-temporal TSI parameters to criterion values from laser measurement (speed) and optoelectric systems (step time and step length) showing acceptable RMSEs for mean speed (0.08 m/s), for step time (0.004 s), and for step length (0.03 m). Top speed interval amplitude showed a significant difference between males (mean: 1.41 m/s) and females (mean: 0.71 m/s) and correlations showed its independence from other sprint parameters. Gender comparisons for validation revealed the expected differences. This pilot study investigated the feasibility of estimating sprint parameters from high-quality tracking data. The proposed method is independent of the data source and allows to automatically obtain general sprint parameters and TSI parameters, including TSI amplitude assessed here for the first time in a competition-like setting.

Within-Match Performance Dynamics - Momentary Strength in Handball.

Abstract: Handball is an Olympic team sport characterized by changes of ball possession, where teams either play on offense or defense. In this paper, we model momentary strength in handball as scoring probabilities based on a double moving average. In this cross-sectional observational study, the aim was to describe the dynamics of momentary strength in handball from both theoretical and practical perspectives. Momentary strength can be used to further characterize the nuances of the sport by identifying different phases in a match. The momentary strength model was applied to the 2019 International Handball Federation (IHF) Men's World Championship. Ninety-six games were analyzed. The results showed that momentary strength could be used to better understand the dynamic interaction process between two teams. The Spearman correlation between the teams' median momentary strength and their final ranks at the Championship was -0.830. Virtually each team faced phases in its matches with a momentary scoring probability lower than 0.10 and with 4 exceptions also higher than 0.90. Twelve out of the 24 teams showed phases with a momentary scoring probability of exactly 0 as well as exactly 1.

Football Match Dynamics Explored by Recurrence Analysis.

Abstract: A widely accepted notion of football matches in performance analysis (PA) is to consider them as dynamic interaction processes with emerging behaviors. The description and analysis of these processes requires specific methods. Recurrence analysis is a technique for analyzing complex systems in many domains like astrophysics, earth sciences, engineering, biology, cardiology, and neuroscience. Its general concept is to examine the recurrence behavior of a system, as in when, how often and how close its trajectory in a phase space returns to a previous state. The aim of the study is to apply recurrence analysis to football matches. Positional data from 21 football matches of a German Bundesliga team were examined. The phase space was made up of the field players' x,y-positions at each second of the match. For each pair of seconds, the average distance of all the players between their positions at these two time points was calculated. Recurrence plots (RPs) were obtained by color-coding these distances. With a recurrence threshold of rt = 9 m and a minimum line length of lmin = 3 s, general recurrence parameters were calculated to characterize the individual recurrence behaviors of each match. Three football-specific recurrence parameters were defined to represent recurrence properties of open play. RPs showed commonalities (typical features indicating set plays and continuous gameplay) as well as unique structures during each match (number, distribution, and sequence of typical features). The recurrence parameters showed several significant correlations with traditional performance indicators like number of goals and passes completed, e.g., the correlation between number of goals and recurrence rate is r = -0.622 (p = 0.003). By extending the sample and design of recurrence studies, there is great potential for recurrence analysis to improve both the practical and theoretical potential of performance analysis.

First Offensive Shot in Elite Table Tennis

Abstract: At the (very) first shots in table tennis, players face a basic tactical decision: either return the ball short and passively or attack it with an offensive shot. In the first case, there is lower risk but no pressure for making the point, in the second case pressure is created, but at the cost of high risk, because the serve and other prior “passive” shots try to make an offensive shot as difficult as possible, typically being short and flat. Thus, the real turntable of a rally is this shot - in this study called “first offensive shot” (FOS) – which is the transition from passive to offensive play. This study investigates the FOS, which is defined as the first shot after the serve without any kind of backspin/side-backspin, for 90 matches (nrally = 7449) of the 2016 Rio Olympic Games. The FOS parameters – laterality, technique and position to the table at the point of contact – and the respective winning probabilities are analysed. The influences of sex and the players’ ranking (resulting in three different match categories) on those parameters are studied. Descriptive statistics about the incidences of the FOSs show that four typical FOSs cover 98% of all FOSs. Chi-square tests reveal a significant relation between sex and these typical FOSs. Regarding the match categories, the tests prove a significant relation between match categories and FOS tactics for both genders. A difference in the FOS tactics between the serving and the receiving player is found as well. The winning probabilities show that using topspin (FH and BH) as FOS was an advantage in every match category, whereas using flip as FOS led mostly to a winning probability below 50% for the FOS player. Except for the FH flip in women’s matches, it was always a bigger advantage for the FOS player if he/she could finish the rally at latest with the follow up attack after the FOS which means that the winning probability for the FOS player decreased in the longer rallies. Compared to prevailing methods in table tennis match analysis, which are based on fixed shot numbers, taking the FOS as object of analyses of rally opening is an innovative new approach focusing on the tactical meaning of shots that is not expressed in shot number.