ViziCal: Accurate Energy Expenditure Prediction for Playing Exergames
In recent years, exercise games have been criticized for not being able to engage their players into levels of physical activity that are high enough to yield health benefits. A major challenge in the design of exergames, however, is that it is difficult to assess the amount of physical activity an exergame yields due to limitations of existing techniques to assess energy expenditure of exergaming activities. For example, the use of heart rate is limited as it can be influenced by psychological factors, such as excitement. Wearable activity monitors predominantly measure locomotion and are limited in being able to capture upper body motions, which are often used in exercise games. EE can be most accurately measured using calorimetric techniques such as metabolic gas analysis systems, but these techniques are expensive and require a significant amount of training. We present Vizical; a low cost and easy to use technique for predicting energy expenditure of exergames in real time.
How it works
We adopt a regression based approach by directly mapping kinematic data collected using a commercially available 3D camera (Microsoft Kinect) to energy expenditure captured using a portable VO2 metabolic system.
Various motion related features are extracted and used to train a regression model.
Given a reasonable amount of training data (phenotypes/exergames), the regression model can then predict energy expenditure of exergaming activities based on kinematic data alone without requiring the player to wear any sensors. Vizical can report current and total energy expenditure in real-time which may allow for developing exergames that stimulate larger amounts of physical activity.
The Kinect sensor can track 20 joints with a high spatial and temporal resolution.