Development of a skateboarding trick classifier using accelerometry and machine learning

Abstract

inclusion of the sport of skateboarding in the Tokyo 2020 Olympic Games. The Tokyo 2020 Skateboarding Commission (TSC), together with the IOC, will oversee the insertion and regulation of the sport of skateboarding in the Olympics (Tokyo…, 2016). Modern skateboarding (Street) uses the urban architecture (banks, walls, steps, handrails) as obstacles, with the skateboarder making use of a variety of different types of tricks to overcome the obstacles (Candotti et al., 2012). Research has shown the practice of skateboarding in urban regions to present a greater risk of injuries and accidents (Everett, 2002), where the most affected are children and untrained beginners (Department…, 2013; Fountain and Meyers, 1996; Forsman and Eriksson, 2001). Given the growing popularity of this sport and its intrinsic risk factor, alternative ways to assist the development of this discipline should be pursued, and the use of computerassisted assessment (CAA) may be a promising tool. Exertion Games, also called exergames, are games where the application of physical effort by the user is necessary (Muller et al., 2008). Studies have already proven that interactive simulations can lead to an improvement in sports performance, such as with skating and ice speed skating (Stienstra et al., 2011), rowing (Broker and Crawley, 2001), and even swimming (Marc et al., 2009).

The classification of skateboarding tricks via transfer learning pipelines

“…The chosen skateboarding tricks in the present investigation are Ollie (O), Nollie Frontside Shuvit (NFS), Frontside 180 (FS180), Pop Shove-It (PS) and Kickflip (KF). The selection of the tricks is non-trivial as it is the most common moves that are executed by a skateboarder in any competition ( Groh, Kautz & Schuldhaus, 2015 ; Corrêa et al, 2017 ). The skateboarding tricks were performed by six 20 ± 7 years old amateur skateboarder with at least 5 years of experience and been executed successfully five times per trick.…”

“…A 10-fold cross-validation technique was employed on the training dataset, and it was shown from the study that an average CA of 89.33% was reported. Conversely, in a recent investigation, Corrêa et al (2017) develop an Artificial Neural Network (ANN) model in classifying five skateboarding tricks. Interestingly, the authors artificially generated the dataset based on the acceleration data reported in Groh, Kautz & Schuldhaus (2015) .…”

Physical fitness and motor ability parameters as predictors for skateboarding performance: A logistic regression modelling analysis

“…Following the completion of the bio-fitness assessments, athletes were afforded additional rest time before their skateboarding skills were assessed. The study centred on the evaluation of five fundamental skateboarding tricks: Ollie, Nollie, Frontside 180, Pop-Shuvit, and Kickflip, all of which had been extensively scrutinized and studied in previous literature [3,[31][32][33][34][35].…”

Skateboarding Injuries in Spain: A Web-Based Survey Approach

“…43 In the following decades until present day, skateboarding has gone through a new period of popularization around the world, 8,24,26,43 leading to its inclusion in the 2020 Olympic Games. 3…”

“…43 In the following decades until present day, skateboarding has gone through a new period of popularization around the world, 8,24,26,43 leading to its inclusion in the 2020 Olympic Games. 3 With the upcoming professionalization of skateboarding in the next few years, the number of skateboarders is expected to keep increasing, alongside the degree of difficulty of the maneuvers performed. 24 This may in turn lead to more injuries related to this sport.…”