BodyPressure -- Inferring Body Pose and Contact Pressure from a Depth Image

TL;DR

This paper presents a deep learning method that infers human body pose and contact pressure from depth images, even with occlusion from bedding, aiding healthcare in preventing pressure injuries.

Contribution

It introduces a novel deep network with an embedded human mesh model and a white-box pressure image generation model, trained on augmented real and synthetic data.

Findings

Successfully infers body pose, outperforming prior methods.

Accurately estimates contact pressure on a 3D human mesh.

Works effectively despite occlusion from bedding.

Abstract

Contact pressure between the human body and its surroundings has important implications. For example, it plays a role in comfort, safety, posture, and health. We present a method that infers contact pressure between a human body and a mattress from a depth image. Specifically, we focus on using a depth image from a downward facing camera to infer pressure on a body at rest in bed occluded by bedding, which is directly applicable to the prevention of pressure injuries in healthcare. Our approach involves augmenting a real dataset with synthetic data generated via a soft-body physics simulation of a human body, a mattress, a pressure sensing mat, and a blanket. We introduce a novel deep network that we trained on an augmented dataset and evaluated with real data. The network contains an embedded human body mesh model and uses a white-box model of depth and pressure image generation. Our network successfully infers body pose, outperforming prior work. It also infers contact pressure across a 3D mesh model of the human body, which is a novel capability, and does so in the presence of occlusion from blankets.