Learn to Infer Human Poses Using a Full-Body Pressure-Sensing Garment

Poses are the fundamentals of human activities and there are growing applications in healthcare, fitness, and virtual reality. Despite massive advances in estimating human poses using cameras, these approaches are not suitable in open areas where people could move freely. Recent advances in wearable pressure sensing systems bring the possibility to estimate human poses in open areas in a more comfortable way compared with existing inertial measurement unit (IMU) approaches. In this study, using a textile-based full-body pressure sensing garment, we collected synchronized pressure and visual data pairs of various human poses. Using a camera-based pose estimation model to generate pose labels, we designed and implemented a deep learning pipeline to infer 3-D human poses using only the full-body pressure data. The pipeline is evaluated using leave-one-out (LOO) cross-validation and it has 98.71-mm joint position error under unseen-participant scenarios. We demonstrate the feasibility of full-body pressure sensing system in estimating human poses and showed that the smart garment could be a possible alternative in estimating human poses in open areas.