Evaluating user's energy consumption using kinect based skeleton tracking

By utilizing the dataset provided by 3DLife/Huawei Challenge of ACM Multimedia, we propose a refreshing application that automatically evaluates player's energy consumption in gaming scenarios by a model with tracked skeleton, which may help users to know their exercise effects and even diet or reduce their weights. We develop a program to compute the energy consumption in real time by analyzing data captured from Microsoft Kinect, and also give a cue in the dynamic interaction. We model 3D human skeleton by joining different body parts with 15 nodes, and decompose player action into rigid body motions of these parts. Amount of energy consumed in the action is calculated as the sum of powers required to overcome gravity of each part. Experimental results show that instantaneous and total energy consumption of different dancers can be stably calculated. The hardware system is based on low-price Kinect, and easily accepted by users. The proposed application also provides a quantitative approach which help users to control their dining and exercise intensity.