Estimating Pose from Pressure Data for Smart Beds with Deep Image-based Pose Estimators

TL;DR

This paper investigates methods for estimating human pose from ambiguous pressure data in smart beds, combining pre-trained image-based pose estimators with domain adaptation techniques to improve accuracy.

Contribution

It introduces a learnable pre-processing step and re-training of existing pose estimators on pressure data, enhancing pose estimation accuracy from vague pressure maps.

Findings

Re-training pre-trained pose estimators on pressure data improves accuracy.

Learnable pre-processing domain adaptation enhances pose estimation from pressure maps.

Combined approach overcomes ambiguity in pressure data for reliable pose detection.

Abstract

In-bed pose estimation has shown value in fields such as hospital patient monitoring, sleep studies, and smart homes. In this paper, we explore different strategies for detecting body pose from highly ambiguous pressure data, with the aid of pre-existing pose estimators. We examine the performance of pre-trained pose estimators by using them either directly or by re-training them on two pressure datasets. We also explore other strategies utilizing a learnable pre-processing domain adaptation step, which transforms the vague pressure maps to a representation closer to the expected input space of common purpose pose estimation modules. Accordingly, we used a fully convolutional network with multiple scales to provide the pose-specific characteristics of the pressure maps to the pre-trained pose estimation module. Our complete analysis of different approaches shows that the combination of learnable pre-processing module along with re-training pre-existing image-based pose estimators on the pressure data is able to overcome issues such as highly vague pressure points to achieve very high pose estimation accuracy.