3D Human Pose Estimation on a Configurable Bed from a Pressure Image

Clever, Henry M.; Kapusta, Ariel; Park, Daehyung; Erickson, Zackory; Chitalia, Yash; Kemp, Charles C.

Title:

3D Human Pose Estimation on a Configurable Bed from a Pressure Image

dc.contributor.author	Clever, Henry M.
dc.contributor.author	Kapusta, Ariel
dc.contributor.author	Park, Daehyung
dc.contributor.author	Erickson, Zackory
dc.contributor.author	Chitalia, Yash
dc.contributor.author	Kemp, Charles C.
dc.contributor.corporatename	Georgia Institute of Technology. Institute for Robotics and Intelligent Machines	en_US
dc.date.accessioned	2019-07-03T17:36:08Z
dc.date.available	2019-07-03T17:36:08Z
dc.date.issued	2018
dc.description.abstract	Robots have the potential to assist people in bed, such as in healthcare settings, yet bedding materials like sheets and blankets can make observation of the human body difficult for robots. A pressure-sensing mat on a bed can provide pressure images that are relatively insensitive to bedding materials. However, prior work on estimating human pose from pressure images has been restricted to 2D pose estimates and flat beds. In this work, we present two convolutional neural networks to estimate the 3D joint positions of a person in a configurable bed from a single pressure image. The first network directly outputs 3D joint positions, while the second outputs a kinematic model that includes estimated joint angles and limb lengths. We evaluated our networks on data from 17 human participants with two bed configurations: supine and seated. Our networks achieved a mean joint position error of 77 mm when tested with data from people outside the training set, outperforming several baselines. We also present a simple mechanical model that provides insight into ambiguity associated with limbs raised off of the pressure mat, and demonstrate that Monte Carlo dropout can be used to estimate pose confidence in these situations. Finally, we provide a demonstration in which a mobile manipulator uses our network’s estimated kinematic model to reach a location on a person’s body in spite of the person being seated in a bed and covered by a blanket.	en_US
dc.identifier.uri	http://hdl.handle.net/1853/61481
dc.subject	Assistive technology	en_US
dc.subject	Pressure imaging	en_US
dc.subject	Configurable bed	en_US
dc.title	3D Human Pose Estimation on a Configurable Bed from a Pressure Image	en_US
dc.type	Text
dc.type.genre	Pre-print
dspace.entity.type	Publication
local.contributor.author	Kemp, Charles C.
local.contributor.corporatename	Rehabilitation Engineering Research Center on Technologies to Support Aging-in-Place for People with Long-Term Disabilities
relation.isAuthorOfPublication	e4f743b9-0557-4889-a16e-00afe0715f4c
relation.isOrgUnitOfPublication	beb39be5-dd4e-4cbd-810d-8b5f852ba609