This study presents several machine learning models tasked with gathering information about what happens in a table tennis match. This information includes the ball's position, identifying serves, and other events such as ball hits and bounces. The TTNet backbone demonstrated superior performance across all tasks, including inference time. The Classification Head achieved high accuracy (94.6%), F1 score (97.2%), and RMSE value (0.014) for ball detection, accurately predicting ball positions. The TTNet model with the Simple Event Head showed promise for event detection (97.5% accuracy, 80.4% F1 score). However, the dataset is heavily imbalanced and the models would probably benefit from a more balanced training set. Serve detection performance was subpar for all models (best F1 score: 42.1%), requiring significant dataset and model reconstruction. All top-performing models achieved fast inference speeds (<4 ms) on various devices, enabling real-time operation even on smartphones.

No description available.

Im Leistungssport wird Techniktraining täglich geplant und bewertet. Gerade die Änderungen in Regeln oder Technikentwicklungen machen Tischtennis zu einem interessanten Anwendungsfeld, wie ein Techniktraining verbessert werden kann. Der Fokus der vorliegenden Arbeit lag nicht nur auf den einzelnen Techniken, sondern ebenfalls darauf wie Übergänge zwischen den Techniken selbst optimiert werden können. Dazu wurde eine Diagnostik für die Techniken und Übergänge (Tischtennis Technikwechsel Leistungsdiagnostik) entwickelt, geprüft und verbessert. Aus den Ergebnissen der Diagnostik wurde eine Intervention der Techniken konzipiert (Phase I), die anschließend selbst- und fremdevaluiert wurde (Phase II). Die Erfahrungen der Intervention der Techniken und deren Evaluation wurden benutzt, um in einer Phase III eine zielgerichtete Trainingsmaßnahme zur Optimierung der Technikübergänge zu gestalten und zu evaluieren. Die Verbesserungen der Interventionsstichprobe gegenüber einer ebenfalls trainierenden Evaluationsstichprobe in kinematischen Analysen der Bewegungen und Trefferleistungen bestätigten die Hypothesen zu einer verbesserten Erreichung der Sollwertvorstellung. Trainingswettkämpfe sowie kurz- und langfristige videobasierte Wettkampfanalysen kamen zu dem Ergebnis, dass die Trainingseffekte auch die Wettkampfleistungen langfristig beeinflussen. Über die konkreten Fragestellungen des Forschungsprojektes hinaus konnten das theoretische Verständnis für sensomotorische Kontrollprozesse bei schnellen Bewegungen sowie methodologische Konsequenzen von langfristigen Evaluationsstudien erarbeitet werden. Ein Praxisteil mit Empfehlungen für die Planung von konkreten Trainingsinhalten schließt die Arbeit ab. / In high level sports is the training of techniques is an everyday event. Table tennis seems an appropriate game based on recent rule changes and developments in techniques, to evaluate how to improve technical training. The focus of this work lies on the training of techniques itself as well as the training of transitions between techniques. To test that a diagnostic (table tennis performance diagnostic for technique transitions) was developed and evaluated. The results from the diagnostic lead to conceptualize an intervention and its evaluation of techniques (phase 1) that was evaluated by inside- group and outside-group evaluators (phase 2). The experience with this intervention and evaluation was used in phase 3 to development trainings and evaluations for the transitions between techniques. The improved performance of the trainings group was superior to an evaluation group with the same training amount in respect of kinematical changes of the movements as well as with accuracy of the ball locations in respect to the assumed changes. Analyses of training competitions as well as videobased evaluations of short-term and long-term performances in real competitions demonstrated that these changes influence positively the overall performance. In addition to these results, the work helped to understand sensorimotor control processes of fast movements and methodological issues of long-term evaluation studies in high level sports. Finally consequences of this research were build in proposed training sessions.

Made available in DSpace on 2014-06-11T19:30:53Z (GMT). No. of bitstreams: 0 Previous issue date: 2010-04-22Bitstream added on 2014-06-13T21:01:33Z : No. of bitstreams: 1 zagatto_am_dr_rcla.pdf: 1108255 bytes, checksum: 38ff0057930b39fd8b9a46337f8fb561 (MD5) / O presente estudo objetivou utilizar o modelo de potência crítica adaptado para o tênis de mesa como um possível procedimento para estimar a capacidade aeróbia e capacidade anaeróbia em teste específico. Foram participantes do estudo 32 mesatenistas do sexo masculino filiados à Confederação Brasileira de Tênis de Mesa e integrantes de cinco equipes de tênis de mesa. Para a execução da tese, o atual trabalho foi dividido em quatro experimentos, possuindo seqüencialmente os devidos propósitos: 1) verificar o perfil fisiológico e as características do jogo de tênis de mesa mensurados em competições oficiais; 2) comparar as respostas fisiológicas, máximas e submáximas, mensuradas em ergômetro específico para o tênis de mesa com as obtidas em ergômetros convencionais; 3) Investigar a aplicação do modelo de potência crítica adaptado para o tênis de mesa como procedimento preditor da capacidade aeróbia, verificando a influência do critério de exaustão e dos modelos matemáticos na determinação desse parâmetro, assim como comparar esses resultados com parâmetros respiratórios máximos e submáximos obtidos em teste incremental especifico; 4) Correlacionar o parâmetro da curvatura constante (W’) da relação hiperbólica entre tempo e potência, sendo a W’ estimada por meio de quatro modelos matemáticos; assim como correlacionar as W’ estimadas com o déficit máximo de oxigênio acumulado e com o trabalho anaeróbio total mensurado em exercícios supramáximos. Como resultados, no experimento 1 foi verificado que o tênis de mesa demandou uma predominância energética aeróbia durante o jogo, porém, com a o metabolismo anaeróbio alático sendo o principal sistema energético nos momentos de esforços. Essas afirmações foram baseadas nos resultados da duração do jogo, duração do rali e baixas respostas lactacidêmicas e da freqüência cardíaca... / The general aim of this thesis was to apply the critical power model for the table tennis specific test as a procedure to estimate aerobic and anaerobic capacities. The study included thirty-two male table tennis players from five teams affiliated to the Brazilian Table Tennis Federation (CBTM). The thesis was divided into four experiments to: 1) Verify the physiological profile and characteristics of table tennis measured in official tournaments; 2) Compare maximal and submaximal physiological responses measured in the table tennis specific test with those measured on a cycloergometer, arm crank, and treadmill (conventional ergometers); 3) Investigate applying the Critical Power model to table tennis as an aerobic capacity predictor, verify the effects of exhaustion criteria (voluntary and technical exhaustion) and mathematical modeling of this parameter, and also to compare results from maximal and submaximal respiratory parameters measured during the specific incremental test; and 4) Correlate the curvature constant parameter (W’) from the Power and time hyperbolic relationship, where W’ was estimated using four mathematical models; and to correlate each W’ estimated with maximal accumulated oxygen deficit (MAOD) and total anaerobic work at supramaximal intensities. Results showed that table tennis presented higher aerobic system predominance during a match, where the phosphagenic energy source was the main mechanism resynthesizing energy during effort periods. This was based on match duration, rally time, low blood lactate response, and sub-threshold heart rate response. Thus, knowing the table tennis physiological profile, experiments 2 and 3 investigated the application of aerobic and anaerobic procedures using specific and conventional ergometers. Experiment 2 revealed different maximal and submaximal physiological responses when comparing the specific test with results... (Complete abstract click electronic access below)

The purpose of this study was to investigate the dynamics of motivational forces in career stages in legendary table tennis players. Participants invited for this study were two highly recognized Swedish table tennis players who achieved major titles during their competitive career. The theoretical frameworks included the self-determination theory (SDT; Ryan & Deci, 1985, 2000), achievement goal theory (AGT; Nicholls, 1989), and the developmental model of transition faced by athletes (Wylleman & Lavallee, 2004). The study was based on in-depth narrative interviews on the field where the researcher stimulated participants to tell their stories in retrospect based on their perceptions of motivational drives across different stages. Results revealed that participants were (a) strongly driven by multiple personal goals (e.g., self-determined, winning major titles), (b) had high perception of ability (e.g., high task and high ego), (c) table tennis was central to their lives, and (d) they were surrounded by facilitative environment. Results are discussed in relation to theoretical frameworks and previous research. / Syftet med föreliggande studien var att undersöka dynamiken i motivationsprosessen genom olika karriärövergångar hos legendariska bordtennisspelare. Två välkända svenska bordtennisspelare deltog i studien som har vunnit stora titlar under sina professionella karriärer. De teoretiska ramverk som användes var self-determination theory (SDT; Ryan & Deci, 1985, 2000), achievement goal theory (AGT; Nicholls, 1989) och developmental model of transition faced by athletes (Wylleman & Lavallee, 2004). Studien var baserad på två djup-narrativa intervjuer där deltagarna stimulerades att i retrospekt berätta hur de upplevde dynamiken i deras motivation i olika karriärövergångar. Resultaten visade att deltagarna var (a) stärkt drivna av multipla personliga mål (själv-bestämd, vinna stora titlar), (b) hade hög upplevd förmåga (hög uppgift och hög prestationsmål), (c) bordtennis var central i deras liv, och (d) de var omringade av stödjande miljöer. De erhållna resultat diskuteras i relation till teoretiska ramverk och tidigare forskning.

The objective of this study was to examine the relationship between dispositional goal orientation (task/ego), perceived motivational climate (mastery/performance) and psychological well-being (such as emotional affect and self-esteem) among elite and non-elite table tennis players. Participants were 85 table tennis players who practice and compete on different levels. The study was carried out quantitatively by assessing perceptions of success questionnaire, perceived motivational climate inventory, positive and negative affect in sport descriptor, and a self-esteem schedule. Results showed no significance difference in goal orientations, perceived motivational climate and psychological well-being between elite and non-elite participants. Further analysis however showed significant differences in motivational and psychological patterns that existed within these two groups. The results are discussed in relation to theoretical frameworks and previous research. / Studiens övergripande syfte var att undersöka förhållandet mellan målorientering (uppgift/tävling), upplevd motivationsklimat (uppgift/tävlingsorienterat) och psykologisk välbefinnande (emotionell affekt och självkänsla) bland svenska bordtennisspelare. I studien deltog 85 svenska bordtennisspelare som tränar och tävlar på olika nivåer. Studien genomfördes kvantitativt och fyra instrument användes: upplevelse av success, upplevelse av motivationsklimat, positiv och negativ affekt och självkänsla. Resultaten visade inga signifikanta skillnader i målorientering, motivationsklimat och psykologiskt välbefinnade mellan grupperna elit och icke-elit. Ytterligare analyser visade signifikanta skillander i motivationella och psykologiska mönster (självkänsla) som förekom innanför grupperna. Resultaten diskuteras i samband med teoretiska referensram och tidigare forskning.

The purpose of this research was to explore the three smashes attacking tactics wich is used by professional table tennis players all over the world. While analysing the game of world‘s elite and top lithuanian men and women players such videotapes of 2005 were used during this work: World Cup (Belgium, October), Lithuania‘s Top 12 competition (Kaunas, December), The Women Euroleague (Kaunas, November). This research incorporates an analyse of 20 players: 6 world men elite players and 6 lithuanian men top players, 4 world class and 4 Lithuanian women players. During the time of research 20 issues were explored: after concluding the results it was estimated how many points are being won by tree smashes attacking conception – completing the service, accepting the service, after completing the serve and winning the point by the third smash, after accepting the service and winning the point by the third smash. Also, it was backhand and forehand smashes explored concerning their effect by using three smashes conception. It emerged that world‘s elite men players win 59,33% points by using three smashes conception while lithuanian men top players win 69,83% points by using the same tactics in the game. World class women players are able to win 75,50% by using an attacking tree points concept, while lithuanian top women players achieve the result of 73,00% by using the same style. World top class players during the first three points win about 33,99% by using their forehand and... [to full text]

Title: Evaluation of the most common injuries and health problems of professional table tennis players Objectives: The main aim of this work is to evaluate the most common injuries and health problems of professional table tennis players in the Czech Republic. Another goal is to determine the level of use of regenerative procedures and compensatory exercises within the training plan of athletes. Methods: The main method used in this thesis was a quantitative research by data analysis from non-standardized questionnaire. The questionnaire was distributed among professional table tennis players who participated actively in the district, regional, league or extra league competition in the Czech Republic or abroad in the 2018/2019 season. A total of 374 questionnaires were processed and evaluated, which corresponds to 62,33 % of the total number of sent questionnaires. Results: Of the 374 table tennis players, 240 were injured (197 men, 43 women), which corresponds to 64,17% of the interviewed players. A total of 361 injuries were recorded. The research confirmed four out of six hypotheses. Statistical significance was noted between the injury and sex, and the statistically significant relationship between the injury and the different playing style was confirmed. Most injuries were in the area of the...

This diploma thesis deals with designing and manipulating a robot for training table tennis. Robot's mechanical construction is based on aluminium profiles supported by various standardized assembly units, such as rotating bearings, plain bearings, threaded rods... The front-end part of the robot, which requires better deformation property and lighter weight, was made from ABS material using 3D rapid prototyping technology. The design of the robot allows its body to rotate around three axises. Thanks to the high dynamical ability, robot can be set to throw balls to various places on the playing table, with different types of ball spin. Balls will be shot out by two rubber wheels, which are attached to two electrical DC motors. By driving the speed of the two motors, we can control the speed of the ball, as well as speed of its spin. All robot's activities are driven by an embedded system designed using microcontroller ATMega128. A firmware for controlling robot's function was writen and flashed into the microcontroller. End-users might communicate with the robot via a system of buttons and a text LCD display. The built robot was tested and it has shown its ability to throw balls to 6 different places of the playing table, at different speeds, with different types of ball spin, and different spin speed, according to the parameters set by user.

It is well understood that multiple video cameras and computer vision (CV) technology can be used in sport for match officiating, statistics and player performance analysis. A review of the literature reveals a number of existing solutions, both commercial and theoretical, within this domain. However, these solutions are expensive and often complex in their installation. The hypothesis for this research states that by considering only changes in ball motion, automatic event classification is achievable with low-cost monocular video recording devices, without the need for 3-dimensional (3D) positional ball data and representation. The focus of this research is a rigorous empirical study of low cost single consumer-grade video camera solutions applied to table tennis, confirming that monocular CV based detected ball location data contains sufficient information to enable key match-play events to be recognised and measured. In total a library of 276 event-based video sequences, using a range of recording hardware, were produced for this research. The research has four key considerations: i) an investigation into an effective recording environment with minimum configuration and calibration, ii) the selection and optimisation of a CV algorithm to detect the ball from the resulting single source video data, iii) validation of the accuracy of the 2-dimensional (2D) CV data for motion change detection, and iv) the data requirements and processing techniques necessary to automatically detect changes in ball motion and match those to match-play events. Throughout the thesis, table tennis has been chosen as the example sport for observational and experimental analysis since it offers a number of specific CV challenges due to the relatively high ball speed (in excess of 100kph) and small ball size (40mm in diameter). Furthermore, the inherent rules of table tennis show potential for a monocular based event classification vision system. As the initial stage, a proposed optimum location and configuration of the single camera is defined. Next, the selection of a CV algorithm is critical in obtaining usable ball motion data. It is shown in this research that segmentation processes vary in their ball detection capabilities and location out-puts, which ultimately affects the ability of automated event detection and decision making solutions. Therefore, a comparison of CV algorithms is necessary to establish confidence in the accuracy of the derived location of the ball. As part of the research, a CV software environment has been developed to allow robust, repeatable and direct comparisons between different CV algorithms. An event based method of evaluating the success of a CV algorithm is proposed. Comparison of CV algorithms is made against the novel Efficacy Metric Set (EMS), producing a measurable Relative Efficacy Index (REI). Within the context of this low cost, single camera ball trajectory and event investigation, experimental results provided show that the Horn-Schunck Optical Flow algorithm, with a REI of 163.5 is the most successful method when compared to a discrete selection of CV detection and extraction techniques gathered from the literature review. Furthermore, evidence based data from the REI also suggests switching to the Canny edge detector (a REI of 186.4) for segmentation of the ball when in close proximity to the net. In addition to and in support of the data generated from the CV software environment, a novel method is presented for producing simultaneous data from 3D marker based recordings, reduced to 2D and compared directly to the CV output to establish comparative time-resolved data for the ball location. It is proposed here that a continuous scale factor, based on the known dimensions of the ball, is incorporated at every frame. Using this method, comparison results show a mean accuracy of 3.01mm when applied to a selection of nineteen video sequences and events. This tolerance is within 10% of the diameter of the ball and accountable by the limits of image resolution. Further experimental results demonstrate the ability to identify a number of match-play events from a monocular image sequence using a combination of the suggested optimum algorithm and ball motion analysis methods. The results show a promising application of 2D based CV processing to match-play event classification with an overall success rate of 95.9%. The majority of failures occur when the ball, during returns and services, is partially occluded by either the player or racket, due to the inherent problem of using a monocular recording device. Finally, the thesis proposes further research and extensions for developing and implementing monocular based CV processing of motion based event analysis and classification in a wider range of applications.