The classification of skateboarding tricks via transfer learning pipelines

Muhammad Amirul Abdullah; Muhammad Ar Rahim Ibrahim; Muhammad Nur Aiman Shapiee; Muhammad Aizzat Zakaria; Mohd Azraai Mohd Razman; Rabiu Muazu Musa; Noor Azuan Abu Osman; Anwar P P Abdul Majeed

doi:10.7717/peerj-cs.680

The classification of skateboarding tricks via transfer learning pipelines

PeerJ Comput Sci. 2021 Aug 18:7:e680. doi: 10.7717/peerj-cs.680. eCollection 2021.

Authors

Muhammad Amirul Abdullah¹, Muhammad Ar Rahim Ibrahim¹, Muhammad Nur Aiman Shapiee¹, Muhammad Aizzat Zakaria¹, Mohd Azraai Mohd Razman¹, Rabiu Muazu Musa², Noor Azuan Abu Osman³, Anwar P P Abdul Majeed^{1

4}

Affiliations

¹ Innovative Manufacturing, Mechatronics and Sports Laboratory, Faculty of Manufacturing and Mechatronics Engineering Technology, Universiti Malaysia Pahang, Pekan, Pahang, Malaysia.
² Centre for Fundamental and Liberal Education, Universiti Malaysia Terengganu, Kuala Nerus, Terengganu, Malaysia.
³ Department of Biomedical Engineering, Faculty of Engineering, Universiti Malaya, Kuala Lumpur, Kuala Lumpur, Malaysia.
⁴ Centre for Software Development & Integrated Computing, Universiti Malaysia Pahang, Pekan, Malaysia.

Abstract

This study aims at classifying flat ground tricks, namely Ollie, Kickflip, Shove-it, Nollie and Frontside 180, through the identification of significant input image transformation on different transfer learning models with optimized Support Vector Machine (SVM) classifier. A total of six amateur skateboarders (20 ± 7 years of age with at least 5.0 years of experience) executed five tricks for each type of trick repeatedly on a customized ORY skateboard (IMU sensor fused) on a cemented ground. From the IMU data, a total of six raw signals extracted. A total of two input image type, namely raw data (RAW) and Continous Wavelet Transform (CWT), as well as six transfer learning models from three different families along with grid-searched optimized SVM, were investigated towards its efficacy in classifying the skateboarding tricks. It was shown from the study that RAW and CWT input images on MobileNet, MobileNetV2 and ResNet101 transfer learning models demonstrated the best test accuracy at 100% on the test dataset. Nonetheless, by evaluating the computational time amongst the best models, it was established that the CWT-MobileNet-Optimized SVM pipeline was found to be the best. It could be concluded that the proposed method is able to facilitate the judges as well as coaches in identifying skateboarding tricks execution.

Keywords: Classification; Machine learning; Skateboarding; Support vector machine; Transfer learning.

Grants and funding

This work is funded by the Ministry of Education, Malaysia through the Fundamental Research Grant Scheme (FRGS/1/2019/TK03/UMP/02/6) and Universiti Malaysia Pahang (RDU1901115). The funders had no role in study design, data collection and analysis, decision to publish, or preparation of the manuscript.