Daniel Link

Real Time Quantification of Dangerousity in Football Using Spatiotemporal Tracking Data.

This study describes an approach to quantification of attacking performance in football. Our procedure determines a quantitative representation of the probability of a goal being scored for every point in time at which a player is in possession of the ball–we refer to this as dangerousity. The calculation is based on the spatial constellation of the player and the ball, and comprises four components: (1) Zone describes the danger of a goal being scored from the position of the player on the ball, (2) Control stands for the extent to which the player can implement his tactical intention on the basis of the ball dynamics, (3) Pressure represents the possibility that the defending team prevent the player from completing an action with the ball and (4) Density is the chance of being able to defend the ball after the action. Other metrics can be derived from dangerousity by means of which questions relating to analysis of the play can be answered. Action Value represents the extent to which the player can make a situation more dangerous through his possession of the ball. Performance quantifies the number and quality of the attacks by a team over a period of time, while Dominance describes the difference in performance between teams. The evaluation uses the correlation between probability of winning the match (derived from betting odds) and performance indicators, and indicates that among Goal difference (r = .55), difference in Shots on Goal (r = .58), difference in Passing Accuracy (r = .56), Tackling Rate (r = .24) Ball Possession (r = .71) and Dominance (r = .82), the latter makes the largest contribution to explaining the skill of teams. We use these metrics to analyse individual actions in a match, to describe passages of play, and to characterise the performance and efficiency of teams over the season. For future studies, they provide a criterion that does not depend on chance or results to investigate the influence of central events in a match, various playing systems or tactical group concepts on success.

Individual ball possession in soccer

This paper describes models for detecting individual and team ball possession in soccer based on position data. The types of ball possession are classified as Individual Ball Possession (IBC), Individual Ball Action (IBA), Individual Ball Control (IBC), Team Ball Possession (TBP), Team Ball Control (TBC) und Team Playmaking (TPM) according to different starting points and endpoints and the type of ball control involved. The machine learning approach used is able to determine how long the ball spends in the sphere of influence of a player based on the distance between the players and the ball together with their direction of motion, speed and the acceleration of the ball. The degree of ball control exhibited during this phase is classified based on the spatio-temporal configuration of the player controlling the ball, the ball itself and opposing players using a Bayesian network. The evaluation and application of this approach uses data from 60 matches in the German Bundesliga season of 2013/14, including 69,667 IBA intervals. The identification rate was F = .88 for IBA and F = .83 for IBP, and the classification rate for IBC was κ = .67. Match analysis showed the following mean values per match: TBP 56:04 ± 5:12 min, TPM 50:01 ± 7:05 min and TBC 17:49 ± 8:13 min. There were 836 ± 424 IBC intervals per match and their number was significantly reduced by -5.1% from the 1st to 2nd half. The analysis of ball possession at the player level indicates shortest accumulated IBC times for the central forwards (0:49 ± 0:43 min) and the longest for goalkeepers (1:38 ± 0:58 min), central defenders (1:38 ± 1:09 min) and central midfielders (1:27 ± 1:08 min). The results could improve performance analysis in soccer, help to detect match events automatically, and allow discernment of higher value tactical structures, which is based on individual ball possession.

A topography of free kicks in soccer

ABSTRACT This study investigates the spatial relationship of performance variables for soccer free kicks. In order to suggest ways in which players might optimise their performance, we collected data from free kicks (<35 m to goal line) of two German Bundesliga seasons (2013/14, 2014/15) (n = 1624). In the analysis, we applied the ISO-map approach using colour gradients to visualise the mean values of a variable on a 2D-map of the pitch. Additionally, variograms were used to describe the degree of spatial dependence of the free kick variables. Results show that DENSITY, TYPE OF PLAY, PLAYERS IN WALL, DISTANCE TO WALL and RULE VIOLATION were strongly spatially dependent. Centrality and proximity to the goal increased the variables PLAYERS IN WALL, RULE VIOLATIONS and INTERRUPTION TIME, and the ratio of goals scored increased from 5.9% (central far) to 10.9% (central near). In 70.9% of the shots, players preferred a switched laterality, which did not result in a higher success rate. Furthermore, there was no statistical advantage for the defensive team when DISTANCE TO WALL was below 9.15 m or when there was a RULE VIOLATION. Crosses had a success rate (i.e., first controlled ball contact after the cross) of 20.8%. Played with natural laterality, they were 5% more successful than with switched laterality. Crosses from the right side outside the penalty box were 10% more successful than from the left side. Therefore, it might be worthwhile practising the defence of balls coming from this side.

Effect of Ambient Temperature on Pacing in Soccer depends on Skill Level.

Abstract Link, D and Weber, H. Effect of ambient temperature on pacing in soccer depends on skill level. J Strength Cond Res 31(7): 1766–1770, 2017—This study examines the influence ambient temperature has on the distances covered by players in soccer matches. For this purpose, 1,211 games from the top German professional leagues were analyzed over the course of the seasons 2011/12 and 2012/13 using an optical tracking system. Data show (a) significant differences in the total distance covered (TDC, in meters per 10 minutes) between the 1. Bundesliga (M = 1,225) and 2. Bundesliga (M = 1,201) and (b) a significant decrease in TDC from neutral (−4 to 13° C, M = 1,229) to warm (≥14° C, M = 1,217) environments. The size of the temperature effect is greater in the 1. Bundesliga (d = 0.30 vs. d = 0.16), although these players presumably have a higher level of fitness. This suggests that better players reduce their exertion level to a greater extent, thus preserving their ability to undertake the high-intensity activities when called upon. No reduction in running performance due to cold (⩽5° C) temperatures was observed.

Seasonal pacing - match importance affects activity in professional soccer

This research explores the influence of match importance on player activity in professional soccer. Therefore, we used an observational approach and analyzed 1,211 matches of German Bundesliga and 2nd Bundesliga. The importance measurement employed is based on post season consequences of teams involved in a match. This means, if a match result could potentially influence the final rank, and this rank would lead to different consequences for a team, such as qualification for Champions League opposed to qualification for Europe League, then this match is classified as important; otherwise not. Activity was quantified by TOTAL DISTANCE COVERED, SPRINTS, FAST RUNS, DUELS, FOULS and ATTEMPTS. Running parameters were recorded using a semi-automatic optical tracking system, while technical variables were collected by professional data loggers. Based on our importance classification, low important matches occurred at the beginning of round 29. A two-way ANOVA indicates significantly increased FAST RUNS (+4%, d = 0.3), DUELS (+16%, d = 1.0) and FOULS (+36%, d = 1.2) in important matches compared to low important ones. For FAST RUNS and FOULS, this effect only exists in Bundesliga. A comparison of the two leagues show that TOTAL DISTANCE COVERED (+3%, d = 0.9), SPRINTS (+25%, d = 1.4) and FAST RUNS (+15%, d = 1.4) are higher compared to 2nd Bundesliga, whilst FOULS is less in Bundesliga (-7%, d = 0.3). No difference in player activity was found between matches at the beginning of a season (round 1–6) and at the end of a season (round 29–34). We conclude that match importance influences player activity in German professional soccer. The most reasonable explanation is a conscious or unconscious pacing strategy, motivated by preserving abilities or preventing injury. Since this tendency mainly exists in Bundesliga, this may suggest that more skilled players show a higher awareness for the need of pacing.

Do We Need Goal Line Technology in Soccer or Could Video Proof Be a More Suitable Choice: A Cost-Benefit-Analysis of Goal Line Technology in Soccer and Thoughts About an Introduction of Video Proof

The aim of this study was to investigate the necessity of goal line technology for top level soccer and compare it to video proof. 1167 games of the 1st and 2nd German Bundesliga were screened for critical goal line decisions as well as other critical goal decisions including penalty calls. 16.8 critical goal line decisions were found per season, of which 76.6 % could directly be resolved by tv-review. On average, 5.0 and 2.8 cases were found respectively in the 1st and 2nd Bundesliga that could justify goal line technology. Furthermore, just 5.0 % of all critical calls concerned goal-line decisions, while 84.3 % involve offside, representing the main reason for critical goal calls. Based on these findings, in terms of a cost-benefit-relation, a video proof could be more suitable than goal line technology. Consequently, we discuss the obstacles and preconditions for the introduction of a video proof in soccer.

Data Analytics in Professional Soccer

This book explores how data analytics can be used for studying performance in soccer. The objectives of sports analytics are varied and are differentiated according to interest group. Professional sport uses the data for game analysis, training load management, injury prevention and to support player transfers. Media companies enrich their reporting with game data analyses, while data companies use sports data as a demonstration domain for the performance of their data analysis products. Sports science can use the enormous data pool to analyze performance structures, to investigate academic claims and to develop new paradigms in the development of theory. On the methodological and technological side, concepts such as data mining, machine learning and big data are becoming increasingly important. The six individual studies in this book are based on spatiotemporal data from the German Bundesliga and were published in scientific journals in 2016 and 2017. The first two studies show how tactical structures in spatiotemporal data can be recognized and used for game analysis with the help of geometric models. The third study uses geostatistical methods to investigate the dependence of various free kick parameters on the position of the free kick. Two further papers deal with the influence of the ambient temperature and the league table position on running activity and actions of players. The sixth study evaluates the effects of the introduction of the free kick vanishing spray. The findings might help coaches to improve the performance of their players and inspire other researchers to advance sports analytics.

Detection of Individual Ball Possession in Soccer

While ball possession usually is considered on team level, a model on player level brings several advantages. We calculate ball possession and control statistics for all players as well as new ball control heat maps to evaluate the players’ performances. Furthermore, a basis for detecting events and tactical structure becomes available. To derive individual ball possession from spatio-temporal data, we present an automatic approach, based both on physical knowledge and machine learning techniques. Moreover, we introduce different ball possession definitions and algorithms to model various grades of ball control. When applied to flawless raw data, the algorithms show precision and recall ratios between 80 and 92 %. With approximately four percentage points less in uncorrected data, the presented algorithms are also reliable in real-world scenarios.

Finding the gap: An empirical study of the most effective shots in elite goalball

This research identifies which shots types in goalball are most likely to lead to a goal and herby provides background information for improving training and competition. Therefore, we observed 117 elite level matches including 20,541 shots played in the regular situation (3 vs. 3) using notational analysis. We characterized the shots by using their target sector (A-E), technique (traditional, rotation), trajectory (flat, bounce), angle (straight, diagonal and outcome (goal, violation, out, blocked). In our data, a χ2-test showed a significantly higher goal rate for men (3.9%) compared to women (3.0%). For men, we found a significantly higher goal rate in the intersection sectors between players C (5.6%), D (4.9%), and in the outer sector A. In sector A, goal rate was higher only for straight shots (6.6%). Technique and trajectory did not affect goal rate for men, but flat shots showed a higher violation rate (3.2%) compared to bounce shouts (2.0%). In womens goalball, goal rate was higher only on sector D (4.4%). Bounce-rotation shots were the most successful (5.5%). We conclude that men should focus on shots to sectors C and D (called pocket) and straight shots to sector A, as long as there are no other tactical considerations. Women should shoot primarily towards the pocket. It might also be worth playing more bounce-rotation shots and practicing them in training.

Validation of electronic performance and tracking systems EPTS under field conditions

The purpose of this study was to assess the measurement accuracy of the most commonly used tracking technologies in professional team sports (i.e., semi-automatic multiple-camera video technology (VID), radar-based local positioning system (LPS), and global positioning system (GPS)). The position, speed, acceleration and distance measures of each technology were compared against simultaneously recorded measures of a reference system (VICON motion capture system) and quantified by means of the root mean square error RMSE. Fourteen male soccer players (age: 17.4±0.4 years, height: 178.6±4.2 cm, body mass: 70.2±6.2 kg) playing for the U19 Bundesliga team FC Augsburg participated in the study. The test battery comprised a sport-specific course, shuttle runs, and small sided games on an outdoor soccer field. The validity of fundamental spatiotemporal tracking data differed significantly between all tested technologies. In particular, LPS showed higher validity for measuring an athlete’s position (23±7 cm) than both VID (56±16 cm) and GPS (96±49 cm). Considering errors of instantaneous speed measures, GPS (0.28±0.07 m⋅s-1) and LPS (0.25±0.06 m⋅s-1) achieved significantly lower error values than VID (0.41±0.08 m⋅s-1). Equivalent accuracy differences were found for instant acceleration values (GPS: 0.67±0.21 m⋅s-2, LPS: 0.68±0.14 m⋅s-2, VID: 0.91±0.19 m⋅s-2). During small-sided games, lowest deviations from reference measures have been found in the total distance category, with errors ranging from 2.2% (GPS) to 2.7% (VID) and 4.0% (LPS). All technologies had in common that the magnitude of the error increased as the speed of the tracking object increased. Especially in performance indicators that might have a high impact on practical decisions, such as distance covered with high speed, we found >40% deviations from the reference system for each of the technologies. Overall, our results revealed significant between-system differences in the validity of tracking data, implying that any comparison of results using different tracking technologies should be done with caution.