Classification of team sport activities using a single wearable tracking device
Introduction
Objective measurement of sports activities is essential for understanding the physical and technical demands related to sports performance (Aughey and Falloon, 2010). It is also important in evaluating the effectiveness of training programs designed to increase performance as well as those targeting both the prevention and rehabilitation of injury (Neville et al., 2010). Fundamental to furthering these understandings is the need to accurately collect specific information relating to the type, intensity and frequency of activities performed (Carling et al., 2009). Consequently, attempts to improve the techniques related to activity analysis in sports have been made in recent years.
At least partially responsible for these improvements are the considerable developments that have occurred in commercially available wearable tracking device technology. Wearable tracking devices typically integrate multiple sensors (e.g., global positioning system [GPS], accelerometer and gyroscope) into a single, versatile unit often worn on the upper back in a sports vest (Kelly et al., 2012). To date, the majority of research has focused on the GPS sensor contained within these devices to obtain basic descriptors of sports activities, such as speed, distance travelled, and the number of high-intensity efforts performed (Cummins et al., 2013). However, evidence suggests that more detailed analysis can be obtained using the accelerometer sensor (Ermes et al., 2008). Specifically, different activity types can be classified based on the features of the accelerometer signal.
McNamara et al. (2015) developed a bowling detection algorithm for cricket. The researchers found that the algorithm was able to classify cricket bowling more effectively in training than game-play, with a maximum accuracy of 98.1% (training). Kelly et al. (2012) applied support vector machine (SVM) and hidden conditional random field algorithms to automatically detect tackling in rugby. The algorithm was able to consistently classify collisions, with a maximum accuracy of 95%. Similarly, Gastin et al. (2013) assessed the concurrent validity of a manufacturer-developed tackle detection algorithm (Catapult Sports), which was compared against video-replay and coded into three intensity categories. The researchers found a maximum classification accuracy of 78%, with tackled players more accurately detected than the players initiating the tackle. However, during game-play the algorithm was only able to correctly detect tackles 18% of the time. Although these findings are promising, more sophisticated and generalisable sport and activity specific algorithms are required (Gastin et al., 2014).
Mitchell et al. (2013) recently proposed a method using a single accelerometer contained within a smartphone worn on the upper-back, with the aim of identifying seven different sporting activities (stationary, walking, jogging, sprinting, hitting a ball, standing tackle, dribbling a ball). An overall activity classification success rate of 75% was achieved using classification approaches that included SVM, Logistic Model Tree (LMT), and a range of Neural Network/Optimisation type classifiers. With the aim of achieving higher classification accuracy, multiple sensors (i.e., both accelerometer and gyroscope) have also been considered in the literature, rather than a single accelerometer sensor alone (e.g. (Leutheuser et al., 2013; Najafi et al., 2003)). Gyroscopes are insensitive to linear accelerations and gravity, and provide essential information pertaining to the rotational motions of the body during human activity (Kunze et al., 2010). As a gyroscope sensor is typically contained within most wearable tracking devices, this would appear to be a feasible approach to aid in the ability to classify of sporting activities.
Another important methodological consideration in the classification literature relates to the duration over which the activity is measured (movement capture duration) for a given classification algorithm (Trost et al., 2012). The optimal duration will ideally be long enough to capture the entire activity as it occurs, while also being short enough to not include any additional activities (Mitchell et al., 2013). Previous work classifying activity type has extracted features in accelerometer data from movement capture durations as short as 0.1 s (Bulling et al., 2014) or as long as 60 s (Trost et al., 2012). In team sports, however, most activities (sprinting, jumping, tackling etc.) can be performed over much shorter durations. For example, the lowest intensity movement (walking) occurs approximately 1.4–2.2 times per second (e.g. (Peacock et al., 2014)). Therefore, much shorter movement capture durations (e.g. 1.5 s or less) may be required to capture activities in team sports. Further, this may improve classification accuracy of these activities, as more periods are available for training (Mannini et al., 2013).
The aims of this study were threefold. First, to determine whether data obtained from wearable tracking device inputs (specifically, gyroscope and accelerometer sensors) alone or in combination can be used to classify team sport-related activities. Second, to determine the ability of three classification algorithms (LMT, RF, SVM) and movement capture durations (0.5, 1.0 and 1.5 s) for feature extraction to classify activities in team sports. Third, to consider the processing time and data collection burdens associated with these methods and identify the best option for practitioners.
Section snippets
Participants
Seventy-six recreationally active, healthy male participants (age 24.4±3.3 years; height 181.8±7.5 m; mass 77.4±11.6 kg; mean±SD) were recruited for participation in the study. All participants were regular competitors in one or more contact-based team sport events per week at the time of testing. The study protocol was approved by the relevant University Human Ethics Advisory Group (HEAG-H 135_2013); all procedures followed ethical guidelines for human research and participants provided written
Results
The accuracy of classifiers per input variation and movement capture duration are presented in Table 1. Throughout all classification iterations LMT greatly outperformed both RF and SVM classifiers, obtaining classification rates 79% or above. As the number of input variables increased from three to seven, the accuracy of the classifiers generally remained the same or increased. The SVM and RF classifiers generally exhibited the strongest accuracy with a 1.5 s movement capture duration, while
Discussion
The results of this study demonstrate that accurate activity classification using accelerometer and gyroscope inputs is achievable in a team-sport simulated circuit. Specifically, results showed that the highest performing algorithm for this purpose was LMT with an overall mean classification rate ranging from 79% to 92%. Further, the highest classification rate was achieved by combining all seven inputs from the accelerometer and gyroscope. Notably, the classification rate was substantially
Conflict of interest statement
None of the authors have financial or other conflicts of interest in regards to this research.
Acknowledgements
None.
References (46)
- et al.
Real-time versus post-game GPS data in team sports
J. Sci. Med. Sport
(2010) - et al.
A study on human activity recognition using accelerometer data from smartphones
Procedia Comput. Sci.
(2014) - et al.
Quantification of tackling demands in professional Australian football using integrated wearable athlete tracking technology
J. Sci. Med. Sport.
(2013) - et al.
Capturing human motion using body-fixed sensors: outdoor measurement and clinical applications
Comput. Animat. Virtual Worlds
(2004) - Bennett, K.P., Bredensteiner, E.J., 2000. Duality and geometry in SVM classifiers. In: Proceedings of the 17th...
- et al.
The reliability of MinimaxX accelerometers for measuring physical activity in Australian football
Int. J. Sports Physiol. Perform.
(2011) Random forests
Mach. Learn.
(2001)- et al.
A tutorial on human activity recognition using body-worn inertial sensors
ACM Comput. Surv.
(2014) - et al.
Performance Assessment for Field Sports
(2009) - et al.
Global positioning systems (GPS) and microtechnology sensors in team sports: a systematic review
Sports Med.
(2013)