Proceedings of the 10th International Symposium on Computer Science in Sports (ISCSS)

Computer vision offers a growing capacity to detect and classify actions in a large range of sports. Since combat sports are highly dynamic and physically demanding, it is difficult to measure features of performance from competition in a safe and practical way. Also, coaches frequently wish to measure the performance characteristics of other competitors. For these reasons it is desirable to be able to measure features of competitive performance without using sensors or physical devices. We present a non-invasive method for extracting pose and features of behaviour in boxing using vision cameras and time of flight sensors. We demonstrate that body parts can be reliably located, which allow punching actions to be detected. Those data can then visualised in a way that allows coaches to analysis behaviour.

Marker-less motion analysis system is the future for sports motion study. This is because it can potentially be applied in real time competitive matches because no marking system is required. The purpose of this study is to observe the suitability and practicality of one of the basic marker-less motion analysis system applications on human movement from sagittal view plane. In this study, the movement of upper and lower extremities of the human body during a vertical jump act was chosen as the movement to be observed. One skilled volleyball player was recruited to perform multiple trials of the vertical jump (n=90). All trials were recorded by one depth camera and one Full HD video camera. The kinematics of shoulder joint was chosen to represent the upper body extremity movement while knee joint was chosen as the representative of the lower body extremity movement during the vertical jump’s initial position to take-off position (IP-TP) and take-off position to highest position (TPHP). Results collected from depth camera-based marker less motion analysis system were then compared with results obtained from a conventional videobased 2-D motion analysis system. Results indicated that there were significant differences between the two analysis methods in measuring the kinematic properties in both lower (knee joint) and upper (shoulder joint) extremity body movements (p < .05). It was also found that a lower correlation between these two analysis methods was more obvious for the knee joint movement [38.61% matched, r = 0.12 (IP-TP) and r =0.01 (TP-HP)] compared to the shoulder joint movement [61.40% matched, r =0.10 (IP-TP) and r =0.11 (TP-HP)].

This paper has designed and developed a platform for testing table tennis ball speed, which are used in the tests of 5 top Chinese female table tennis players in three of their practices. The results show that the ball speeds of LI and DING are faster than those of LIU, ZHU and CHEN. LI’s ball speed over the net is the fastest in all exercises, especially in forehand loop-drive against backspin and forehand moving loop-drive. DING’s ball speed over the net is the second-fastest in different practices (except for forehand loop-drive in the Two to One practice). LIU, ZHU and CHEN’s ball speeds are slower, among which, the relatively slower ball speeds over the net were LIU’s backhand loop-drive in the Two to One practice, ZHU’s forehand loop-drive in the Two to One exercise and in the forehand loop-drive against backspin, and CHEN’s forehand moving loop-drive.

Detecting events in table tennis using monocular video sequences for match-play officiating is challenging. Here a low-cost monocular video installation generates image sequences and, using the Horn-Schunck Optical Flow algorithm, ball detection and location processing captures sudden changes in the ball’s motion. It is demonstrated that each abrupt change corresponds to a distinct event pattern described by its combined velocity, acceleration and bearing. Component motion threshold values are determined from the analysis of a range of table tennis event video sequences. The novel event classifier reviews change in motion data against these thresholds, for use in a rules based officiating decision support system. Experimental results using this method demonstrate an event classification success rate of 95.9%.

The 3D ball trajectory provides us quantitative technical or tactical information (e.g. the ball speed of serve). The 3D trajectory can be reconstructed by multiple camera system or single camera system. The single camera 3D reconstruction method is better than the multiple camera one, because it is convenient for the video from television. The existing monocular 3D reconstruction method suffers from the model-drifting problem. We solve this problem using a new cost function. Experimental result shows that our method is more accurate than classical method, because our cost function is a mixture of the physical model and the geometric model.

Recent years have seen an increasing number of introduction of IT innovations in top level sports in almost each competitive nation. Practical experiences show that it is a long way with many pitfalls leading from a technological innovation to its successful introduction in sports. The idea of this paper is to make use of management concepts brought forward in economy to provide a conceptual framework for this task. The benefit would be to circumvent common problems, to prepare innovators for typical ones and to improve each stakeholder’s understanding of the process. Product and innovation life cycle theory, innovation management theory, and customer relationship management theory are described in the paper. Applicability to the problem under investigation is discussed, and important contributions as well as conceptual differences are pointed out. As examples for best practice, two IT innovations introduced recently in German top level sports are analyzed. National teams (male and female) in the Paralympic sport goalball and Olympic beach-volleyball introduced a computer based match analysis system. One may conclude that it is helpful to borrow conceptual knowledge from economy to better understand the introduction of IT innovations in top level sports.

In football clubs there are different isolated sources of information. The result is a fundamental need for a central club information system (CIS) for the management. The development of such a system is the purpose of this research. An analysis of the current situation at football clubs has to be done. Based on that, the structure and design for the software solution could be developed. A prototype and a field test will improve the understanding of the needs and habits of the employees at the club. This new information will run into the further development. That iterative process creates a software model that could fulfill the requirements of a central CIS.

Although frame-by-frame is one of the important operation to see sports movement precisely, it is not implemented in the streaming videos on the Internet. This article introduces Smart-method, a new method of frame-byframe on the streaming videos. It is based on the combination of two methods, streaming and download; streaming is used for playback, the image download is used for frame-by-frame operation, and these operations are switched smoothly, users will not notice these switches. Smart-method is not only enables to see sports movement precisely it opens various applications possible on the Internet; attaching meta-data of the sports videos, flexible thumbnail, and editing (cut and join the videos) on the Internet.

The goal of the present work was to create a computational system that supports the design of strategies and the match simulation based on those strategies. A formal model of team strategy and match dynamics supported the specification of the computational system. In this model, team strategy was defined as a discrete dynamic system. The specification of individual action rules enables the team players to organize the collective action in every state of the system. A play is modelled by a sequence of compatible pairs of states. The system implementation encompasses a designing tool, whose resultant strategies are used as the input in a simulator capable of recognizing match states and applying the defined strategy to plan actions. Besides the inherent contribution to the investigation of team sports performance features, the presented framework may be helpful in other scientific areas, such as those that investigate cooperative actions in competitive environments and to the design of video-games with a greater realism, approximating them to real match simulators.

Success in a soccer match is usually measured by goals. However, in order to yield goals, successful tactical pre-processing is necessary.

If analyzing a match with the focus on ”success”, promising tactical activities including vertical passes with control win in the opponent’s penalty area have to be the focus. Whether or not a pass is able to crack the opponent’s defence depends on the tactical formations of both the opponent’s defence and the own offence group.

The methodical part of the contribution consists of three steps: (1) The first step describes how to analyze the formations of tactical groups by means of an artificial neural network, which is integrated in the DyCoN-tool. I.e. the positions of the players are condensed to those of tactical groups, and the formations of the tactical groups are mapped to a small number of characteristic patterns. In this way, the teams’ activities can be reduced to interactions of tactical patterns, making it much easier to automatically detect regular and/or striking tactical features. Those tactical features build the context for measuring success, as described in the following steps:

(2) Successful passes from a passing to a receiving player of a team are necessary preconditions for opening or continuing successful attacks. The software SOCCER is able to automatically calculate those passes based on the position data of the players and the ball. Along with the information from (1) it can be recognized, which types of formation interaction are helpful for generating successful or ”dangerous” passes.

(3) Up to this point, ”successful” just means that the receiving player effectively achieves control of the ball. Based on the Voronoi-approach, the pass is seen as more successful and actually ”dangerous”, if it causes a higher rate of spatial control in the opponent’s penalty area. The Voronoi-tool calculates tactical space control and therefore helps to measure the tactical success of a pass.

The combination of the described steps of automatic position-based analyses can be helpful for a deeper understanding of match dynamics and measuring tactical success.

The tools

DyCoN

,

SOCCER

and

Voronoi

have been developed by J. Perl, University of Mainz, in cooperation with D. Memmert, DSHS Cologne.

Single-leg balance test is one of the most common assessment methods in order to evaluate the athletes’ ability to perform certain sports actions efficiently, quickly and safely. The balance and postural control of an athlete is usually affected after a lower limb injury. This study proposes an interval type- 2 fuzzy logic (FL) based automated classification model for single-leg balance assessment of subjects after knee surgery. The system uses the integrated kinematics and electromyography (EMG) data from the weight-bearing leg during the balance test in order to classify the performance of a subject. The data are recorded through wearable wireless motion and EMG sensors. The parameters for the membership functions of input and output features are determined using the data recorded from a group of athletes (healthy/having knee surgery) and the recommendations from physiotherapists and physiatrists, respectively. Four types of fuzzy logic systems namely type-1 non-singleton interval type-2 (NSFLS type-2), singleton type-2 (SFLS type-2), non-singleton type-1 (NSFLS type-1) and singleton type-1 (SFLS type-1) were designed and their performances were compared. The overall classification accuracy results show that the interval type-2 FL system outperforms the type-1 FL system in classifying the balance test performance of the subjects. This pilot study suggests that a fuzzy logic based automated model can be developed in order to facilitate the physiotherapists and physiatrists in determining the impairments in the balance control of the athletes after knee surgery.

Neural networks can be applied to many predictive data mining applications due to their power, flexibility and relatively easy operations. Predictive neural networks are very useful for applications where the underlying process is complex, such as in classification using a mix of nominal and ratio level variables and for predictive validity based on classification modelling. A neural network can approximate a wide range of statistical models without requiring the researcher to hypothesize in advance certain relationships between the dependent and independent variables. The two major applications are multilayer perceptron (MLP) and radial basis function (RBF) procedures. In contrast to MLP networks, in the RBS networks it is only the output units that have a bias term. Discriminant analysis (or discriminant function analysis) based on classification modelling is applied to classify cases into the values of a categorical dependent variable, usually a dichotomy. Logistic regression is useful for situations in which you want to be able to predict the presence or absence of a characteristic or outcome based on values of a set of predictor variables. It is similar to a linear regression model but is suited to models where the dependent variable is dichotomous. The aim of this research was to apply both neural networks, discriminant function analysis (a more traditional statistical approach under the general linear model) and logistic regression and compare their ability as statistical techniques to classify the different genders based nine sports psychological constructs to measure motivations to participate in masters sports. The sample consisted of 3687 male and 3488 female master’s athletes who participated in the 2009 World Masters Games and represented a volunteer/convenient sample in the study and a cross-sectional non-experimental research design. The Motivations of Marathoners Scales (MOMS) psychometric instrument assessed participant motivation by nine constructs/factors using factor scores from a 56 item seven Likert type survey instrument measuring motivations to participate. These factors were health orientation, weight concern, personal goal achievement, competition, recognition, affiliation, psychological coping, life meaning and self-esteem. The accuracy of the solutions were assessed with neural networks, by classification accuracy using both test and holdout samples, predicted-byobserved chart, ROC curve, cumulative gains and lift charts, independent variable importance and normalised importance; and discriminant function analysis by both original and cross-validation samples, lambda values, p-values, tolerance, F to remove and in stepwise discriminant analysis by the hierarchy of inclusion steps. Similar methods were applied when assessing classification accuracy using logistic regression. The results in terms of MLP analysis was overall correct percent of 64.4% and the order of importance was competition, selfesteem, affiliation, recognition, weight concern, health orientation, goal achievement, psychological coping and life meaning. In terms of RBF analysis training sample overall correct percent was 60.5% and order of importance was competition, affiliation, recognition, psychological coping, weight concern, life, meaning, self-esteem, goal achievemnt and health orientation. For the discriminant analysis the overall correct classification rate was 63.3% and for logistic regression 63.0% and the stepwise entry order into both analyses was affiliation, competition, self-esteem, recognition, weight concern and health orientation. The classification accuracies based on MLP, discriminant analysis and logistic regression were very similar in outcome for both the classification of gender and combined classification accuracy. None of the classification techniques based on neural network analyses and multivariate method of discriminant analysis and logistic regression were overtly superior to each other. Although it is important to note the RBF neural network displayed classification accuracy slightly lower than the other three methods.

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.

Capturing human motion performances with inertial measurement units constitutes the future of mobile sports analysis, but requires sophisticated methods to extract relevant information out of the sparse and unintuitive inertial sensor data. Kinematic data like body joint positions and segment orientations can be estimated from a sensor’s accelerations and angular velocities. For further analysis, it is necessary to develop intelligent retrieval strategies that can make sense of the underlying motion information. In this paper, we therefore discuss how to retrieve main motion determinants from raw and processed inertial sensor data. We design methods that extract a motion’s significant technical elements as well as methods that combine several measurable elements over time to extract motion features responsible for the aesthetic impression of a sports performance. In a neural network environment those feature extractors can then give the possibility to automatically evaluate and rank different performances in mobile training and competition systems, which could contribute to a better measurability and objectivity in performance-oriented sports as gymnastics and figure skating.

Aikido is a Japanese martial art inspired by harmony and intelligent exploitation of human body movements, a consequence of which is believed to be a minimisation of impacts. This study measures the effectiveness of aikido-specific movements to minimise impact forces, and arguably the risk of injuries, in person-to-floor contact. In one experiment, we measured a significant reduction of impact forces with the ground for aikido experts during a forward roll in comparison to untrained participants. This first initial result encourages further studies of aikido techniques in areas such as safety and efficacy in sport exercise, safety during full body motion involving falls and impacts, transfer to human-robot interaction and training of elderly people.

Pace control and green reading have been highlighted as important aspects of a golfer’s arsenal when it comes to putting. The purpose of this study was to compare the ball roll characteristics across eight different surfaces and more specifically analyse the distance it takes for a golf ball to achieve pure rolling motion. Two different methods of collecting putting data were used during this study; a putting robot and a human subject. For each surface thirty putts were tracked for the first 40cm of their travel, namely; a putting mat, rubber, MFC, compact carpet, brass, PTFE, MDF and nitrile rubber, via a high speed camera (360 frames per second). A numerical model was used to determine the mean coefficient of kinetic friction from each of the eight surfaces. Results showed that the surface with the highest coefficient of friction (

μ

= 0.40), allowed the ball to enter true roll at the earliest stage (3.94”), whereas the surface with the lowest coefficient of friction (

μ

= 0.11), allowed the ball to enter pure roll at the latest stage (16.77”). Knowledge of this negative relationship may have great significance for golf coaches, players who are looking to improve their green reading skills, and golf course designers/greens keepers who are trying to further understand and improve putting greens.

A pass is an important action in soccer. Amongst other things, it allows moving the ball across the pitch quickly to create scoring opportunities and score goals. Passing performances are usually analyzed using descriptive measures such as number of passes or passing accuracy, however, neglecting the game context. This paper provides an approach to assess passes with respect to the tactical behavior of the participating teams. Results illustrate the application of the model by analyzing the passes played by players of different playing positions. Depending on the game context the players on different playing positions face different environments and, therefore, play passes of different tactical difficulty.

There is a perception that performances in athletic events, such as the sprints, throws distance and hurdles events are converging for the top athletes in each event where access to quality training methods and performances at international competitions are readily available for international ranked athletes. Some researchers cite biological reasons that may explain the suggested convergent tends in athletics. The research hypothesis and aim was to evaluate if performance convergence was occurring using the method of regression analysis of the mean of standard deviations, an index of performance dispersion or divergence, for the top 20 male and female athletes across the majority of athletic events from years 1960 to 2012. The results indicated that most male events have reached stasis, neither converging nor diverging whereas female events are currently undergoing performance convergence. Factors such as access to high performance coaches, sports scientist, relevant sports nutritionists and quality medical support are producing the level playing field that is now so level that minimal performance diversity exists between the top 20 male athletes across many events. The reverse situation applies to female athletes who are still displaying performance convergence and who are progressing towards a level playing field.

The on-going technical progress in pervasive computing influences our daily activities more and more. In sports, smartphone apps are used to support athletes during training - either by giving plain physiological or motivating feedback. The Mobile Motion Advisor (MMA) is such kind of system, developed for the use in school children’s physical education. A school class resembles a highly inhomogeneous group regarding their physical fitness. Hence, considering absolute performance parameters might not be an appropriate way to grade the school children’s efforts.With the introduction of the relative Activity Index (

rAI

), we propose a method that approaches fair grading based on the technologies of the MMA. The

rAI

is a calculated value that resembles the relative activity of an individual within a group, based on the number of steps of each individual. As we found out,

rAI

correlates significantly (

r

= 0.620, p < 0.01) with the V̇

O

2

max

which allows to deduce an estimated individual

$rAI_{est_m}$

. Comparing the estimated

rAI

est

with the actual

rAI

m

may enable us to grade efforts within the context of the games dynamics and the individual fitness.

Goalball is one of the paralympic disciplines designed for visually impaired athletes. Two teams, each consisting of three players try to score goals by rolling the ball into the oppositions’ net. All players wear additional blindfolds to guarantee that players are equally impaired. The ball contains bells allowing players to echolocate its movement. Goalball-specific software was developed for performance analysis (“GoalScout”, “GoalView” and “GoalTrack”). For practical and intuitive scouting purposes the software runs on tablet PCs. Additionally, positional data extracted form video sequences provides precise information. GoalTrack accurately measures the speed of the ball. The purposes of this project were to: a) design a software prototype that efficiently analyzes performance and, b) analyzes key aspects of Goalball. Bowling patterns were characterized for all teams and players. Significant scoring sectors were identified (Sector 3 and 7; X

2

= 7.50, p≤.006). A correlation between ball speed and success rate is, especially in women games, statistically significant (Men: r = .65; Women: r = .90).

This study tries to assess the impact of different tactical behaviors on the winning probability in table tennis by mathematical simulation. Using discrete states of the game and transitions between them by means of the Markov chain model, the numerical derivation of winning probabilities is calculated under assumption of the Markov chain property. The method introduced in this study improves the traditional model by omitting the necessity to perform a second modeling step to define the difficulty of tactical behaviors. Application of our method on table-tennis shows meaningful results like the identification of long rallies as highly influencing stroke types and the effects of risky play on winning probability in different game situations.

Setting an appropriate training load is one of the key elements for the success of exergames. Especially for the cardiovascular training, the adaptation of the current training load in accordance to an individually predetermined target training load plays an important role. In this paper, a new approach for the estimation and prediction of an individual’s heart rate based on a monoexponential formula is presented and evaluated using statistical data. The estimation and prediction of the heart rate is a key factor for the calculation of adequate exertion parameters and therefore for the adaptation and personalization of exertion games, i.e. games that use whole-body exercises for game control. The tests reveal that the course of the heart rate response to changes of load bouts is not stable. Only a differential influence of gender on the HR course depending on the particular load bout can be found.

A soccer player’s ability to make an ”effective” pass in a play situation is considered one of the key skills characterizing successful performance in elite soccer (Bush, Barnes, Archer, Hogg, & Bradley, 2015; Hughes & Franks, 2005; Mackenzie & Cushion, 2013). However, although there is ample evidence in the literature that passing behavior is important it is much less clear what actually characterizes a ”good” pass. One common topic investigated with respect to passing behavior in elite soccer is the frequency of passing events and their correlation with game performance (Lago-Peńas, Lago-Ballesteros, Dellal, & Gómez, 2010; Liu, Gomez, Lago-Penas, & Sampaio, 2015). Results from this line of research show for example that the number of passes made during the FIFA World cup finals between 1966 and 2010 continuously increased (Wallace & Norton, 2014) and that the number of crosses and assists are positively related to game performance (Lago-Peńas et al., 2010; Luhtanen, Belinskij, Häyrinen, & Vänttinen, 2001). Similar, Hughes and Franks (2005) found that longer passing sequences increase the goal scoring likelihood (see also Yiannakos & Armatas, 2006). Although all these studies provide valuable information regarding the importance of passing behavior in elite soccer it remains unclear what characterizes successful passing. Accordingly, it is not known which effects individual passes exert on concrete game play situations which impedes the application of research findings by practitioners. Here, we introduce a novel approach to evaluate individual passing behavior during game play using Voronoi cells to investigate changes in space control.

Using the lactate threshold for training prescription is the gold-standard, although there are several open questions. One open question is: What is the best fitting method for the load-lactate data points? This investigation re-analyses over 3500 lactate diagnostic datasets in swimming. Our evaluation software examines six different fitting methods with two different minimization criteria (RMSE and SE). Optimization of parameters of the functions is put in excecution with gradient descent. From a mathematical point of view, the double phase model, which consists of two linear regression lines, shows the least errors (

RMSE

min

0.254 ± 0.172;

SE

min

0.311 ± 0.210). However, this method cannot be used for every further determination of lactate thresholds. Some threshold determination models need a single curve. In these cases, the exponential function shows the least errors (

RMSE

min

0.846 ± 0.488;

SE

min

1.196 ± 0.689). This confirms the default fitting method used in practice.

Bobsleigh start is a simple action requiring the crew to push as hard as possible and gain maximum initial velocity of the sled at the start. However, detailed computer analysis based on velocity and acceleration data shows that timing of loading play a very important role. In this work we demonstrate that a very important performance parameter commonly called exit velocity can be use as both target and performance measurement. The analysis of time profiles allowed us to modify the timing of the loading and gain nearly 1km/h on the exit speed.

Research in the field of sports performance is constantly developing new technology to help extract meaningful data to aid in understanding in a multitude of areas such as improving technical or motor performance. Video playback has previously been extensively used for exploring anticipatory behaviour. However, when using such systems, perception is not active. This loses key information that only emerges from the dynamics of the action unfolding over time and the active perception of the observer. Virtual reality (VR) may be used to overcome such issues. This paper presents the architecture and initial implementation of a novel VR cricket simulator, utilising state of the art motion capture technology (21 Vicon cameras capturing kinematic profile of elite bowlers) and emerging VR technology (Intersense IS-900 tracking combined with Qualisys Motion capture cameras with visual display via Sony Head Mounted Display HMZ-T1), applied in a cricket scenario to examine varying components of decision and action for cricket batters. This provided an experience with a high level of presence allowing for a real-time egocentric view-point to be presented to participants. Cyclical user-testing was carried out, utilisng both qualitative and quantitative approaches, with users reporting a positive experience in use of the system.

In order to effectively support motor learning in Virtual Reality, real-time analysis of motor actions performed by the athlete is essential. Most recent work in this area rather focuses on feedback strategies, and not primarily on systematic analysis of the motor action to be learnt. Aiming at a high-level understanding of the performed motor action, we introduce a two-level approach. On the one hand, we focus on a hierarchical motor performance analysis performed online in a VR environment. On the other hand, we introduce an analysis of cognitive representation as a complement for a thorough analysis of motor action.

Nowadays, many tracking systems in football provide positional data of players but only a few systems provide reliable data of the ball. The tracking quality of many available systems suffers from high ball velocities up to 120km/h and from the occlusion of both the players and the ball.

Radio-based local positioning systems use sensors integrated in the ball and located on the players’ back or near the shoes to avoid such issues. However, a qualitative evaluation of the tracking precision of radio-based systems is often not available and to the best of our knowledge there are actually no studies that deal with the positional accuracy of ball tracking.

In this paper we close this gap and use the RedFIR radio-based locating system together with a ball shooting machine to repeatedly simulate realistic situations with different velocities in an indoor environment. We compare the derived positions from high speed camera footage to the positions provided by the RedFIR system by means of root mean square error (RMSE) and Bland-Altman analysis.

We found an overall positional RMSE of 12.5cm for different ball velocities ranging from 45km/h to 61km/h. There was a systematic bias of 11.5cm between positions obtained by RedFIR and positions obtained by the high speed camera. Bland-Altman analysis showed 95% limits of agreement of [ 21.1cm, 1.9cm]. Taking the ball diameter of 22cm into account these results indicate that RedFIR is a valid tool for kinematic, tactical and time-motion analysis of ball movements in football.

This paper presents a novel stance phase detection procedure based on observations from a foot-mounted inertial measurement unit (IMU). A frequency-tracking algorithm from the field of audio analysis was applied to the inertial signal to obtain information about gait cycle duration. Afterwards, this information was used to determine the stance phase point for the next gait cycle. This periodicity-based stance-phase detection procedure was found to be superior to traditional thresholdbased algorithms, significantly reducing the number of insertion and deletion errors, with less dependence on selected threshold values.

Wearable technologies are a growing industry with significant potential in different aspects of health and fitness. Gamification of health and fitness, on the other hand, has recently become a popular field of research. Accordingly, we believe that wearable devices have the potential to be utilized towards gamification of fitness and exercise. In this paper, we first review several popular activity tracking wearable devices, their characteristics and specifications, and their application programming interface (API) capabilities and availabilities, which will enable them to be employed by third party developers for the purpose at hand. The feasibility and potential advantages of utilizing wearables for gamification of health and fitness are then discussed. Finally, we develop a pilot prototype as a case-study for this concept, and perform preliminary user studies which will help further explore the proposed concept.

Spatial competencies are one of the most prominent gender differences in view of cognitive abilities. Psychological and interdisciplinary games studies proved a general malleability of spatial competencies. In addition, some studies prove that spatial competencies can be improved by playing First- Person Shooter games. Furthermore studies show that individual spatial experiences are of great importance for the development of spatial competencies. Consequently individual differences in spatial competencies are constituted by learning, training and development factors. Playing video games count to these experiences and are therefore considered as beneficial means of training intervention.

This research project examines suitable training methods for spatial competencies on the basis of gesture-controlled sports games. The aim is to test the effectiveness of this kind of training. It is expected that participants in a 9 hour training intervention will improve their spatial competencies after playing a mimetic Dance game. A small N study shows that significant effects can be expected when studying the optimal sample size.

Spatial abilities are the basic precondition to process visual-spatial information no matter whether that information derives from a digital or a real source. They play an important role in many different areas of life. Vocation, leisure, education and sport are affected by perceptional abilities. However, in sport science this field of research is quite underestimated. Mental rotation tasks occur for example during the early phase of motor learning processes when a motor imagery as an internal representation develops to govern the imitation of the presented model. While IT-based applications are applied to support the imagery process, their actual impact on learning may depend on the level of spatial abilities. To study the relations between spatial abilities and the development of a proper motor imagery two different test instruments, MRT BIO (Mental Rotation Test for biological objects) and PiCaST (Picture Card Selection Test), were developed. Those testing tools and the associated research options are presented in the current paper.

To fully exploit the potentials of e-learning, learners have to take more responsibility for their own learning. According to models of selfregulated learning (SRL), learners have to actively engage in planning, execution and reflection of their learning activities. The purpose of this paper is to present a study on the effects of an SRL training on multimedia learning in sport science.

Twenty students attending a course in biomechanics of sport were randomly assigned to a self-regulation training (SRT) or a no-training (NO-SRT) group. The SRT group underwent an SRL training. Before and after the learning period of 2 weeks, the students’ knowledge and self-confidence was tested. Although the SRT group spent more time with the program than the NO-SRT group, there was no learning benefit. Test performance of both groups significantly increased from pretest to posttest.