Search

Data analysis for athletic performance optimization and injury prevention is of tremendous interest to sports teams and the scientific community. However, sports data are often sparse and hard to obtain due to legal restrictions, unwillingness to share, and lack of personnel resources to be assigned to the tedious process of data curation. These constraints make it difficult to develop automated systems for analysis, which require large datasets for learning. We therefore present SoccerMon, the largest soccer athlete dataset available today containing both subjective and objective metrics, collected from two different elite women's soccer teams over two years. Our dataset contains 33,849 subjective reports and 10,075 objective reports, the latter including over six billion GPS position measurements. SoccerMon can not only play a valuable role in developing better analysis and prediction systems for soccer, but also inspire similar data collection activities in other domains which can benefit from subjective athlete reports, GPS position information, and/or time-series data in general., (© 2024. The Author(s).)

The quantification of peak locomotor demands has been gathering researchers' attention in the past years. Regardless of the different methodological approaches used, the most selected epochs are between 1-, 3-, 5- and 15-minutes time windows. However, the selection of these time frames is frequently arbitrary. The aim of this study was to analyse the peak locomotor demands of short time epochs (15, 30, 45, and 60 seconds) in women's football, with special emphasis over the high-speed metrics. During two seasons, the match physical performance of 100 female football players was collected with Global Positioning System units (STATSports Apex). Peak locomotor demands for the selected variables were calculated by using a 1-second moving average approach. For statistical procedures, linear mixed modelling was used, with total distance, high-speed running distance (>16 km∙h-1), sprint distance (>20 km∙h-1), and acceleration and deceleration distance (±2.26 m∙s-2) considered as the dependent variables and the epoch lengths (15, 30, 45, and 60 seconds) considered as the independent variables. A novel finding was the high ratio observed in the 15 seconds epochs of high-speed running distance and sprint distance (77.6% and 91.3%, respectively). The results show that most peak high-speed demands within 60 seconds are completed within just 15 seconds. Thus, intensity-related variables, such as high-speed metrics, would be better contextualised and adapted into training practices if analysed in shorter epoch lengths (15-30 seconds), while longer periods might be used for volume-related metrics (i.e., total distance), depending on the purpose of the analysis., Competing Interests: The authors have read the journal’s policy and have the following competing interests: IB is affiliated with CIFI2D, which is financed by the Portuguese Foundation for Science and Technology (https://doi.org/10.54499/UIDB/05913/2020) outside of the submitted work. This does not alter our adherence to PLOS ONE policies on sharing data and materials. There are no patents, products in development or marketed products associated with this research to declare., (Copyright: © 2024 Baptista et al. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.)

This observational study aimed to analyze external training load in highly trained female football players, comparing starters and non-starters across various cycle lengths and training days., Method: External training load [duration, total distance [TD], high-speed running distance [HSRD], sprint distance [SpD], and acceleration- and deceleration distance [AccDecdist] from 100 female football players (22.3 ± 3.7 years of age) in the Norwegian premier division were collected over two seasons using STATSports APEX. This resulted in a final dataset totaling 10498 observations after multiple imputation of missing data. Microcycle length was categorized based on the number of days between matches (2 to 7 days apart), while training days were categorized relative to match day (MD, MD+1, MD+2, MD-5, MD-4, MD-3, MD-2, MD-1). Linear mixed modeling was used to assess differences between days, and starters vs. non-starters., Results: In longer cycle lengths (5-7 days between matches), the middle of the week (usually MD-4 or MD-3) consistently exhibited the highest external training load (~21-79% of MD TD, MD HSRD, MD SpD, and MD AccDecdist); though, with the exception of duration (~108-120% of MD duration), it remained lower than MD. External training load was lowest on MD+2 and MD-1 (~1-37% of MD TD, MD HSRD, MD SpD, MD AccDecdist, and ~73-88% of MD peak speed). Non-starters displayed higher loads (~137-400% of starter TD, HSRD, SpD, AccDecdist) on MD+2 in cycles with 3 to 7 days between matches, with non-significant differences (~76-116%) on other training days., Conclusion: Loading patterns resemble a pyramid or skewed pyramid during longer cycle lengths (5-7 days), with higher training loads towards the middle compared to the start and the end of the cycle. Non-starters displayed slightly higher loads on MD+2, with no significant load differentiation from MD-5 onwards., Competing Interests: The authors have declared that no competing interests exist., (Copyright: © 2024 K. Winther et al. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.)

Peak locomotor demands are considered as key metrics for conditioning drills prescription and training monitoring. However, research in female football has focused on absolute values when reporting match demands, leading to sparse information being provided regarding the degrees of variability of such metrics. Thus, the aims of this study were to investigate the sources of variability of match physical performance parameters in female football players and to provide a framework for the interpretation of meaningful changes between matches.54 female players from four top-level clubs were monitored during one season. GPS APEX (STATSports, Northern Ireland), with a sampling frequency of 10 Hz, were used in 60 official matches (n = 393) to determine the full-match and 1-min peak locomotor demands of total distance (TD), high-speed running distance (HSRD), sprint distance (SpD), accelerations and decelerations (Acc/Dec) and peak speed (Pspeed). For each variable, the between-team, between-match, between-position, between-player, and within-player variability was estimated using linear mixed-effect modelling.With exception to SpD (29.4 vs. 31.9%), all other metrics presented a higher observed match-to-match variability in the 1-min peaks than in the full-match (6.5 vs. 4.6%; 18.7% vs. 15.9%; 12.9 vs. 11.7%; for TD, HSRD and Acc/Dec, respectively). With the exception of SpD, higher changes in 1-min peaks than in full-match values are required to identify meaningful changes in each variable.Different sources of variability seem to impact differently the match physical performance of female football players. Furthermore, to identify meaningful changes, higher changes in 1-min peaks than in full-match values are required.

Detecting events in videos is a complex task, and many different approaches, aimed at a large variety of use-cases, have been proposed in the literature. Most approaches, however, are unimodal and only consider the visual information in the videos. This paper presents and evaluates different approaches based on neural networks where we combine visual features with audio features to detect (spot) and classify events in soccer videos. We employ model fusion to combine different modalities such as video and audio, and test these combinations against different state-of-the-art models on the SoccerNet dataset. The results show that a multimodal approach is beneficial. We also analyze how the tolerance for delays in classification and spotting time, and the tolerance for prediction accuracy, influence the results. Our experiments show that using multiple modalities improves event detection performance for certain types of events. [ABSTRACT FROM AUTHOR]

The current gold standard for extracting highlight clips from soccer games is the use of manual annotations and clippings, where human operators define the start and end of an event and trim away the unwanted scenes. This is a tedious, time-consuming, and expensive task, to the extent of being rendered infeasible for use in lower league games. In this paper, we aim to automate the process of highlight generation using logo transition detection, scene boundary detection, and optional scene removal. We experiment with various approaches, using different neural network architectures on different datasets, and present two models that automatically find the appropriate time interval for extracting goal events. These models are evaluated both quantitatively and qualitatively, and the results show that we can detect logo and scene transitions with high accuracy and generate highlight clips that are highly acceptable for viewers. We conclude that there is considerable potential in automating the overall soccer video clipping process. [ABSTRACT FROM AUTHOR]

Developing systems for the automatic detection of events in video is a task which has gained attention in many areas including sports. More specifically, event detection for soccer videos has been studied widely in the literature. However, there are still a number of shortcomings in the state-of-the-art such as high latency, making it challenging to operate at the live edge. In this paper, we present an algorithm to detect events in soccer videos in real time, using 3D convolutional neural networks. We test our algorithm on three different datasets from SoccerNet, the Swedish Allsvenskan, and the Norwegian Eliteserien. Overall, the results show that we can detect events with high recall, low latency, and accurate time estimation. The trade-off is a slightly lower precision compared to the current state-of-the-art, which has higher latency and performs better when a less accurate time estimation can be accepted. In addition to the presented algorithm, we perform an extensive ablation study on how the different parts of the training pipeline affect the final results. [ABSTRACT FROM AUTHOR]

Introduction: The COVID-19 outbreak with partial lockdown has inevitably led to an alteration in training routines for football players worldwide. Thus, coaches had to face with the novel challenge of minimizing the potential decline in fitness during this period of training disruption. Methods: In this observational pre- to posttest study involving Norwegian female football players (18.8 ± 1.9 years, height 1.68 ± 0.4 m, mass 61.3 ± 3.7 kg), we investigated the effects of a prescribed home-based and group-based intervention, implemented during the COVID-19 lockdown, on maximal muscular force production and high velocity variables. Specifically, maximal partial squat strength one repetition maximum (1RM), counter movement jump (CMJ) and 15 m sprint time were assessed 1 week prior to the lockdown and 12 weeks after the onset of lockdown. We also collected training content and volume from the prescribed training program and self-reported perceived training quality and motivation toward training. Results: We observed no change in 1RM [pretest: 104 ± 12 kg, posttest: 101 ± 11 kg (P = 0.28)], CMJ height [pretest: 28.1 ± 2.3 cm, posttest: 26.8 ± 1.9 (P = 0.09)], and 15 m sprint time [pretest: 2.60 ± 0.08 s, posttest: 2.61 ± 0.07 s (P = 0.52)]. Conclusion: Our findings suggest that a prescribed home-based and group-based intervention with increased training time devoted to strength, jump, and sprint ability, and regulated to obtain a sufficient infection control level is feasible and effective to preserve strength, jumping, and sprinting abilities of high-level female football players during a ∼ 3-month period of a pandemic-induced lockdown. [ABSTRACT FROM AUTHOR]

The importance of winning has increased the role of performance analysis in the sports industry, and this underscores how statistics and technology keep changing the way sports are played. Thus, this is a growing area of interest, both from a computer system view in managing the technical challenges and from a sport performance view in aiding the development of athletes. In this respect, Bagadus is a real-time prototype of a sports analytics application using soccer as a case study. Bagadus integrates a sensor system, a soccer analytics annotations system, and a video processing system using a video camera array. A prototype is currently installed at Alfheim Stadium in Norway, and in this article, we describe how the system can be used in real-time to playback events. The system supports both stitched panorama video and camera switching modes and creates video summaries based on queries to the sensor system. Moreover, we evaluate the system from a systems point of view, benchmarking different approaches, algorithms, and trade-offs, and show how the system runs in real time. [ABSTRACT FROM AUTHOR]

Background: Maximal strength increments are reported to result in improvements in sprint speed and jump height in elite male football players. Although similar effects are expected in females, this is yet to be elucidated. The aim of this study was to examine the effect of maximal strength training on sprint speed and jump height in high-level female football players. Methods: Two female football teams were team-cluster-randomized to a training group (TG) performing maximal strength training (MST) twice a week for 5 weeks, or control group (CG) doing their regular pre-season preparations. The MST consisted of 3–4 sets of 4–6 repetitions at ≥85% of 1 repetitions maximum (1RM) in a squat exercise. Sprint speed and jump height were assessed in 5-, 10- and 15 m sprints and a counter-movement jump (CMJ) test, respectively. Nineteen participants in TG (18.3 ± 2.7 years) and 14 in CG (18.3 ± 2.4 years) completed pre- and posttests and were carried forward for final analyses. Results: There was no improvement in neither of the sprint times (p > 0.36), nor jump height (p = 0.87). The players increased their 1RM in squats (main of effect of time: p < 0.00, pη2 = 0.704), and an interaction effect of time x group was observed (p < 0.00, pη2 = 0.516) where the TG increased their 1RM more than the CT (between subjects effects: p < 0.001, pη2 = 0.965). Conclusions: MST improved maximal strength in female football players to a large extent; however, the improvement in maximal strength did not result in any transference to sprint speed or jump height. Trial registration: This study was registered at clinicaltrials.gov PRS (Protocol registration and results System) with the code NCT04048928, 07.08.2019, retrospectively registered. [ABSTRACT FROM AUTHOR]