In-bed posture classification and limb identification

Ostadabbas, Sarah; Pouyan, Maziyar Baran; Nourani, Mehrdad; Kehtarnavaz, Nasser

doi:10.1109/biocas.2014.6981663

Cited by 63 publications

(43 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Accordingly, candidate methods should be able to recognize multiple body parts simultaneously in darkness and varying cover conditions. As far as we know, none of the existing method can perfectly address all aforementioned standards except PM-based method in which the best one turns out to be the work by [11] with comparable granularity. With close accuracy performance as shown in Fig.…”

Section: Comparison With Pm-based Pose Estimationmentioning

confidence: 99%

“…Currently, besides self-reports obtained from the patients and/or visual inspection by the caregivers, in-bed pose estimation methods mainly rely on the use of pressure mapping (PM) systems. Although PM-based methods are effective at localizing areas of increased pressure and even automatically classifying overall postures [11], the pressure sensing mats are expensive and require frequent maintenance, which have prevented PM pose monitoring solutions from achieving large-scale popularity.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Seeing Under the Cover: A Physics Guided Learning Approach for In-bed Pose Estimation

Liu

Ostadabbas

2019

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

Human in-bed pose estimation has huge practical values in medical and healthcare applications yet still mainly relies on expensive pressure mapping (PM) solutions. In this paper, we introduce our novel physics inspired visionbased approach that addresses the challenging issues associated with the in-bed pose estimation problem including monitoring a fully covered person in complete darkness. We reformulated this problem using our proposed Under the Cover Imaging via Thermal Diffusion (UCITD) method to capture the high resolution pose information of the body even when it is fully covered by using a long wavelength IR technique. We proposed a physical hyperparameter concept through which we achieved high quality groundtruth pose labels in different modalities. A fully annotated in-bed pose dataset called Simultaneously-collected multimodal Lying Pose (SLP) is also formed/released with the same order of magnitude as most existing large-scale human pose datasets to support complex models' training and evaluation. A network trained from scratch on it and tested on two diverse settings, one in a living room and the other in a hospital room showed pose estimation performance of 98.0% and 96.0% in PCK0.2 standard, respectively. Moreover, in a multi-factor comparison with a state-of-the art in-bed pose monitoring solution based on PM, our solution showed significant superiority in all practical aspects by being 60 times cheaper, 300 times smaller, while having higher pose recognition granularity and accuracy.

show abstract

Section: Comparison With Pm-based Pose Estimationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Seeing Under the Cover: A Physics Guided Learning Approach for In-bed Pose Estimation

Liu

Ostadabbas

2019

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

show abstract

“…For this approach different methodologies are used including: pressure amplitude value change embedded in a logistic regression model [3], pressure image analysis [12], [17], Bayesian classifier [10], and an algorithm combining normalization, Eigenspace projection, and a kNN classifier [24]. The approaches try to distinguish up to 13 different positions [16] showing difficulties with distinguishing the prone from the supine position. In the studies, data from a different number of subjects were collected.…”

Section: Related Workmentioning

confidence: 99%

“…In the studies, data from a different number of subjects were collected. In most cases, data was collected in a simulated setting, from two [10], three [3], six [24], nine [16] and 20 [17] participants. Liu et al [12] collected data from 14 subjects in a simulated, and three in a real world situation.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Wearable accelerometer based extended sleep position recognition

Fallmann

Veen

Chen

et al. 2017

2017 IEEE 19th International Conference on E-Health Networking, Applications and Services (Healthcom)

View full text Add to dashboard Cite

Abstract-Sleep positions have an impact on sleep quality and therefore need to be further analyzed. Current research on position tracking includes only the four basic positions. In the context of wearable devices, energy efficiency is still an open issue. This research presents a way to detect eight positions with higher granularity under energy efficient constraints. Generalized Matrix Learning Vector Quantization is used, as it is a fast and appropriate method for environments with limited computation resources, and has not been seen for this kind of application before. The overall model trained on individuals performs with an averaged accuracy of 99.8%, in contrast to an averaged accuracy of 83.62% for grouped datasets. Real world application gives an accuracy of around 98%. The results show that energy efficiency will be feasible, as performance stays similar for lower sampling rate. This is a step towards a mobile solution which gives more insight in person's sleep behaviour.

show abstract

Human Body Parts Tracking from Pressure Data: Toward Effective Pressure Injury Assessment

Lastre-Dominguez

Hajari

et al. 2021

Lecture Notes in Computer Science

View full text Add to dashboard Cite

In-bed posture classification and limb identification

Cited by 63 publications

References 7 publications

Seeing Under the Cover: A Physics Guided Learning Approach for In-bed Pose Estimation

Seeing Under the Cover: A Physics Guided Learning Approach for In-bed Pose Estimation

Wearable accelerometer based extended sleep position recognition

Human Body Parts Tracking from Pressure Data: Toward Effective Pressure Injury Assessment

Contact Info

Product

Resources

About