Four-joint motion data based posture classification for immersive postural correction system

In the modern age, it is important for people to maintain a good sitting posture because they spend long hours sitting. Posture correction treatment requires a great deal of time and expenses with continuous observation by a specialist. Therefore, there is a need for a system with which users can judge and correct their postures on their own. In this paper, we propose a four joint-based motion capture system for building immersive postural correction system. The system collects the subject’s postures, and features are extracted from the collected data to build a database. The data in the DB are classified into normal and abnormal postures after posture learning using the K-means clustering algorithm. An experiment was performed to classify the posture from the joints’ rotation angles and positions; the normal posture judgment reached a success rate of 99.79 %. This result suggests that the features of the four joints can be used to judge and help correct a user’s posture through application to a spinal disease prevention system in the future.