Summary

Description

We propose to develop ESPRIT: an Exercise Sensing and Pose Recovery Inference Tool, in support of NASA's effort in developing crew exercise technologies for astronaut health and fitness. ESPRIT is a single camera system that monitors the exercise activities of the crew, detects markers placed on the body and other image features, recovers 3D kinematic information of the human body pose, and compiles statistical data about the exercise activities. There are two main challenges for motion capture using a single camera: (1) lack of depth information, and (2) partial occlusion of parts of the body. To overcome these challenges, the proposed framework relies on strong priors on human body pose, shape, and motion dynamics to resolve pose ambiguities. Besides marker locations, it extracts other image features that provide additional cues for recovering pose. It combines both discriminative and generative approaches to achieve robust pose estimation and tracking performance.