A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf
.
Filters
In-bed Pressure-based Pose Estimation using Image Space Representation Learning
[article]
2020
arXiv
pre-print
However, pose estimation models fail to generalize when facing images acquired from in-bed pressure sensing systems. ...
Results confirm the effectiveness of our method by the high visual quality in the generated images and the high pose estimation rates achieved. ...
With the recent advances in deep learning, a number of data-driven methods have been developed for pose estimation using natural camera-based images for a wide range of applications such as animation, ...
arXiv:1908.08919v2
fatcat:g3tg5wfyebfo3n5f64zqtuvej4
3D Human Pose Estimation on a Configurable Bed from a Pressure Image
[article]
2018
arXiv
pre-print
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. ...
Pressure-Image-based Work Prior pressure-image-based pose estimation work has fit 2D kinematic models to pressure image features. ...
arXiv:1804.07873v2
fatcat:kzwntfkotbbldnfauel5vnb7zm
Bodies at Rest: 3D Human Pose and Shape Estimation from a Pressure Image using Synthetic Data
[article]
2020
arXiv
pre-print
We also present PressureNet, a deep learning model that estimates human pose and shape given a pressure image and gender. ...
We describe a physics-based method that simulates human bodies at rest in a bed with a pressure sensing mat, and present PressurePose, a synthetic dataset with 206K pressure images with 3D human poses ...
We apply this insight to the problem of using a pressure image to estimate the 3D human pose and shape of a person resting in bed. ...
arXiv:2004.01166v1
fatcat:3xa2kosowrabfhf5fqesut75wu
Towards Accurate Cross-Domain In-Bed Human Pose Estimation
[article]
2021
arXiv
pre-print
Majority of the contactless human pose estimation algorithms are based on RGB modality, causing ineffectiveness in in-bed pose estimation due to occlusions by blankets and varying illumination conditions ...
In this paper, we propose a novel learning strategy comprises of two-fold data augmentation to reduce the cross-domain discrepancy and knowledge distillation to learn the distribution of unlabeled images ...
in-bed pose estimation. ...
arXiv:2110.03578v1
fatcat:sm2ykvy5oneu3blq6hsgtr2yeq
Video-Based Inpatient Fall Risk Assessment: A Case Study
[article]
2021
arXiv
pre-print
We propose an approach that leverages recent advances in human localisation and skeleton pose estimation to extract spatial features from video frames recorded in a simulated environment. ...
However, in-bed fall risk assessment systems have received less attention in the literature. ...
Fig. 4 . 4 Representation of the human key points detected in a selected image.
Fig. 5 . 5 Representation of the distance feature estimation. ...
arXiv:2106.07565v1
fatcat:k7pbvjes4bghxgtttw3wr2mir4
Guest Editorial: Machine Vision Applications
2017
International Journal of Computer Vision
The method adaptively learns spatial-spectral dictionary through considering "high correlation across spectra" and "non-local self-similarity over space" in the degraded HIS. ...
The authors extend the Support Vector Data Description (SVDD) for adaptively learn an incremental classifier based on a source classifier. ...
is learned to describe the human activities using the binary dynamic system (BDS) representation. ...
doi:10.1007/s11263-017-0990-1
fatcat:tytmngwqejdezjsjoj766kqxom
Smart healthcare system-a brain-like computing approach for analyzing the performance of detectron2 and PoseNet models for anomalous action detection in aged people with movement impairments
2021
Complex & Intelligent Systems
The objective of this research is to apply real-time pose estimation models for object detection and abnormal activity recognition with vision-based complex key point analysis. ...
Object detection based on bounding box with a mask is successfully implemented with detectron2 deep learning model. ...
Pressure sensors associated with the fiber cables measures floor pressure which is used as an input to a BackProjection algorithm which reconstructs the pressure images and using that postures will be ...
doi:10.1007/s40747-021-00319-8
fatcat:apc7chp4zbcbtl2hm3gt3zakai
A Vision-Based System for In-Sleep Upper-Body and Head Pose Classification
2022
Sensors
system that can work on remote subjects, as it uses images captured by a home security camera. ...
Recent research shows that head and body pose play a vital role in affecting sleep quality. ...
A domain adaption-based training strategy [28] is proposed to estimate in-bed human poses using RGB and thermal images. ...
doi:10.3390/s22052014
pmid:35271162
pmcid:PMC8914692
fatcat:nqtdkpscxrhtzoy6xgk72mqq5y
Deep Learning-Based Human Pose Estimation: A Survey
[article]
2022
arXiv
pre-print
Human pose estimation aims to locate the human body parts and build human body representation (e.g., body skeleton) from input data such as images and videos. ...
Although the recently developed deep learning-based solutions have achieved high performance in human pose estimation, there still remain challenges due to insufficient training data, depth ambiguities ...
[43] focused on the HPE of the rest position in bed from pressure images which were collected by a pressure sensing mat.
3D HPE Summary 3D HPE has made significant advancements in recent years. ...
arXiv:2012.13392v4
fatcat:ypnqtq3sbncr5fuujif2dhqwji
Heuristic Weakly Supervised 3D Human Pose Estimation in Novel Contexts without Any 3D Pose Ground Truth
[article]
2022
arXiv
pre-print
HW-HuP learns partial pose priors from public 3D human pose datasets and uses easy-to-access observations from the target domain to iteratively estimate 3D human pose and shape in an optimization and regression ...
Monocular 3D human pose estimation from a single RGB image has received a lot attentions in the past few year. ...
Visual inspection of the SOTA 3D human pose and shape estimation models compared to our heuristic weakly-supervised 3D human pose estimation model (HW-HuP), when applied on an in-bed pose image taken from ...
arXiv:2105.10996v2
fatcat:37jtkfeylrhtnjxvw5n6ma5tsi
"BAM!" Depth-Based Body Analysis in Critical Care
[chapter]
2013
Lecture Notes in Computer Science
This representation allow us to develop metrics to estimate bed occupancy, body localization, body agitation and sleeping position. ...
We propose the use of a Bed Aligned Map (BAM) to analyze the patient's body. We use a depth camera to localize the bed, estimate its surface and divide it into 10 cm × 10 cm cells. ...
Right: The Bed Aligned Map (BAM) is a height based representation aligned to the surface of the bed (best viewed in color). ...
doi:10.1007/978-3-642-40261-6_56
fatcat:6jgk4o4glve4rad5hcqr5m3pvu
Bodies Uncovered: Learning to Manipulate Real Blankets Around People via Physics Simulations
[article]
2022
arXiv
pre-print
While robots present an opportunity to provide physical assistance to older adults and people with mobility impairments in bed, people frequently rest in bed with blankets that cover the majority of their ...
In addition, we transfer simulation-trained policies to a real mobile manipulator and demonstrate that it can uncover a blanket from target body parts of a manikin lying in bed. ...
In future work, this could be replaced with methods for pose estimation of a human covered by blankets in bed using pressure images from a pressure mat on a bed [40] or depth images from an overhead ...
arXiv:2109.04930v2
fatcat:xvgwj6a5c5gqxkem36tmne7si4
Activity summarisation and fall detection in a supportive home environment
2004
Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004.
Learned models of spatial context are used in conjunction with a tracker to achieve these goals. ...
Summarisation in terms of semantic regions is demonstrated using acted scenes through automatic recovery of the instructions given to the actor. ...
Instead, the person's position in the image along with a coarse representation of their shape and orientation in the image were tracked using an ellipse so that the state at time t was e t = (x t , y t ...
doi:10.1109/icpr.2004.1333768
dblp:conf/icpr/Nait-CharifM04
fatcat:prhzthgierbztck6yuciw3lav4
Populating 3D Scenes by Learning Human-Scene Interaction
[article]
2021
arXiv
pre-print
Second, we show that POSA's learned representation of body-scene interaction supports monocular human pose estimation that is consistent with a 3D scene, improving on the state of the art. ...
POSA provides an effective representation to search for "affordances" in the scene that match the likely contact relationships for that pose. ...
We also show that POSA can be used for estimating human pose from an RGB image, and that the body-centered HSI representation improves accuracy. ...
arXiv:2012.11581v2
fatcat:3mwk46dcm5bs5j54cwesjmo7sm
Towards Contactless Patient Positioning
2020
IEEE Transactions on Medical Imaging
This has in-turn led to understaffed hospitals unable to handle new patient influx. ...
Our system has already been used, and had a positive impact on, hospitals and technicians on the front lines of the COVID-19 pandemic, and we expect to see its use increase substantially globally. ...
based on the estimated mesh and camera parameters, and E θ and E β are the same priors (for pose and shape respectively) as in SMPLify. ...
doi:10.1109/tmi.2020.2991954
pmid:32365022
fatcat:2wckwhlbmbdcjj37ogk6pih56u
« Previous
Showing results 1 — 15 out of 15,139 results