Privacy Preservation for eSports: A Case Study Towards Augmented Video Golf Coaching System

This paper presents a solution for filtering personally identifiable information for developments of augmented video coaching systems and exergames applied on a golf case study. Aligned with eWaste reduction, this study included multiple low-cost video sources including new and obsolete video cameras, mobile devices, and Microsoft Kinect to capture and convert motion data as a silhouette-based video. The algorithm development combined computer vision techniques with design science. The silhouette-based video produced was sufficient for a coach to provide analysis of static and dynamic critical features of golf swings (e.g. stance, tempo and swing plane). In looking beyond eSport systems, the achieved outcomes (robustness to colours, contrast, diverse video resolutions and lightning intensity changes) and insights are universally applicable to enable human-or AI-based motion activity analytics. The next-generation of IoE/IoT and ubiquitous systems will benefit from presented algorithms integrated in smart homes, post-surgery/rehabilitation environments, elderly activity/safety monitoring, sport umpiring and other motion analysis contexts and environments where video privacy is considered paramount.