Pose stability analysis is the key to understanding lo-comotion and control of body equilibrium, with applica-tions in numerous fields such as kinesiology, medicine, and robotics. In biomechanics, Center of Pressure (CoP) is used in studies of human postural control and gait. We propose and validate a novel approach to learn CoP from pose of a human body to aid stability analysis. More specifically, we propose an end-to-end deep learning architecture to regress foot pressure heatmaps, and hence the CoP locations, from 2D human pose derived from video. We have collected a set of long (5min +) choreographed Taiji (Tai Chi) sequences of multiple subjects with synchronized foot pressure and video data. The derived human pose data and correspond-ing foot pressure maps are used jointly in training a convo-lutional neural network with residual architecture, named PressNET. Cross-subject validation results show promis-ing performance of PressNET, significantly outperforming the baseline method of K-Nearest Neighbors. Furthermore, we demonstrate that our computation of center of pres-sure (CoP) from PressNET is not only significantly more accurate than those obtained from the baseline approach but also meets the expectations of corresponding lab-based measurements of stability studies in kinesiology.

@article{funk2018learning,
                    title={Learning dynamics from kinematics: Estimating 2d foot pressure maps from video frames},
                    author={Funk, Christopher and Nagendra, Savinay and Scott, Jesse and Ravichandran, Bharadwaj and Challis, John H and Collins, Robert T and Liu, Yanxi},
                    journal={arXiv preprint arXiv:1811.12607},
                    year={2018}
                  }