Instructional mirroring applied in basketball shooting technique

Abstract

Human posture recognition is a very promising field of computer vision and it is applied in the areas of personal health care, human-computer-interaction, sports etc. In this paper a non-contact view-based approach of human body movement analysis is introduced using Microsoft Kinect V2 sensor. Moreover, there is a developing interdisciplinary scientific field which is trying to integrate modern technology into sports. Computer technology may prove a valuable supportive tool for (a) athletes of all ages to improve their technical skills, and (b) advanced coaching. The aim of this study is to integrate educational technology and sports in order to support the training of young athletes and boost their performance. This research utilizes Kinect V2 as a 3D depth camera in order to apply body tracking of a young athlete during a shooting attempt. The shooting movement is mirrored to the computer screen with instructions showing the right shooting technique. The application was developed using Microsoft Development Kit 2.0 (SDK) and it was evaluated in a basketball camp. The results of the evaluation were very encouraging concerning the ease of use and the usefulness of this application.