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

@article{Liu2019SeeingUT,
  title={Seeing Under the Cover: A Physics Guided Learning Approach for In-Bed Pose Estimation},
  author={Shuangjun Liu and Sarah Ostadabbas},
  journal={ArXiv},
  year={2019},
  volume={abs/1907.02161}
}
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 vision-based 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… Expand
Towards Accurate Cross-Domain In-Bed Human Pose Estimation
TLDR
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 real world conditions. Expand
Simultaneously-Collected Multimodal Lying Pose Dataset: Towards In-Bed Human Pose Monitoring under Adverse Vision Conditions
TLDR
This paper introduces the Simultaneously-collected multimodal Lying Pose dataset, which includes in-bed pose images from 109 participants captured using multiple imaging modalities including RGB, long wave infrared, depth, and pressure map, and presents a physical hyper parameter tuning strategy for ground truth pose label generation under extreme conditions such as lights off and being fully covered by a sheet/blanket. Expand
Multimodal In-bed Pose and Shape Estimation under the Blankets
TLDR
A pyramid scheme to effectively fuse the different modalities in a way that best leverages the knowledge captured by the multimodal sensors to reduce the negative effects of the occlusion from blankets is proposed. Expand
Bodies at Rest: 3D Human Pose and Shape Estimation From a Pressure Image Using Synthetic Data
TLDR
A physics-based method that simulates human bodies at rest in a bed with a pressure sensing mat and incorporates a pressure map reconstruction network that models pressure image generation to promote consistency between estimated 3D body models and pressure image input is described. Expand
Seeing under the cover with a 3D U-Net: point cloud-based weight estimation of covered patients
TLDR
This work proposes a novel deep learning framework, which comprises two 3D CNN modules solving the given task in two separate steps, and presents a novel pipeline to estimate the weight of patients, which are covered by a blanket. Expand
Heuristic Weakly Supervised 3D Human Pose Estimation in Novel Contexts without Any 3D Pose Ground Truth
TLDR
A heuristic weakly supervised solution, called HW-HuP to estimate 3D human pose in contexts that no ground truth 3D data is accessible, even for fine-tuning, and is able to be extended to other input modalities for pose estimation tasks. Expand
BodyPressure - Inferring Body Pose and Contact Pressure from a Depth Image
TLDR
This work focuses 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. Expand
Robust Multi-modal 3D Patient Body Modeling
TLDR
A novel robust dynamic fusion technique is presented that facilitates flexible multi-modal inference, resulting in accurate 3D body modeling even when the input sensor modality is only a subset of the training modalities, hence achieving an important flexibility towards developing cost-effective clinically-deployable machine learning models. Expand
Multi-Person Pose Estimation Using Thermal Images
TLDR
This study introduces ThermalPose, which is a neural network system that parses thermal images and extracts accurate 2D human poses and uses lightweight neural network models that can be easily matched to the design requirements for Internet-of-Things applications. Expand
Graph-Based Deep Learning for Medical Diagnosis and Analysis: Past, Present and Future
TLDR
This survey thoroughly review the different types of graph architectures and their applications in healthcare in a systematic manner, organized by their domain of application including functional connectivity, anatomical structure, and electrical-based analysis. Expand
...
1
2
...

References

SHOWING 1-10 OF 14 REFERENCES
In-Bed Pose Estimation: Deep Learning With Shallow Dataset
TLDR
The idea of employing a pre-trained convolutional neural network model trained on large public datasets of general human poses and fine-tuning the model using its own shallow in-bed IRS dataset and using the HOG rectification method to deal with the unconventional pose perspective is explored. Expand
Patient MoCap: Human Pose Estimation Under Blanket Occlusion for Hospital Monitoring Applications
TLDR
This work proposes a learning-based method that allows to automatically infer 3D patient pose from depth images using a combination of convolutional neural network and recurrent neural network, which is trained on a large database that covers a range of motions in the hospital bed. Expand
2D Human Pose Estimation: New Benchmark and State of the Art Analysis
TLDR
A novel benchmark "MPII Human Pose" is introduced that makes a significant advance in terms of diversity and difficulty, a contribution that is required for future developments in human body models. Expand
Inner Space Preserving Generative Pose Machine
TLDR
An image “inner space” preserving model that assigns an interpretable low-dimensional pose descriptor (LDPD) to an articulated figure in the image, called inner space preserving generative pose machine (ISP-GPM) is introduced. Expand
Clustered Pose and Nonlinear Appearance Models for Human Pose Estimation
TLDR
A new annotated database of challenging consumer images is introduced, an order of magnitude larger than currently available datasets, and over 50% relative improvement in pose estimation accuracy over a state-of-the-art method is demonstrated. Expand
Stacked Hourglass Networks for Human Pose Estimation
TLDR
This work introduces a novel convolutional network architecture for the task of human pose estimation that is described as a “stacked hourglass” network based on the successive steps of pooling and upsampling that are done to produce a final set of predictions. Expand
"BAM!" Depth-Based Body Analysis in Critical Care
TLDR
This work proposes the use of a Bed Aligned Map BAM to analyze the patient's body, using a depth camera to localize the bed, estimate its surface and divide it into 10 cm × 10 cm cells, which represents the average cell height over the mattress. Expand
Bed Status Detection for Elder-Care Center
  • Jiun-Ren Ding
  • Computer Science
  • 2009 16th International Conference on Systems, Signals and Image Processing
  • 2009
TLDR
This paper focuses on the bed status detection with single IP camera for the chronic ailment and act slowly elders in the elder-care center (EC) based on simple and fast motion estimation and binary area matching algorithms, which can automatically remind the professional nurse which one of six elders will go to or leaving bed in a room. Expand
In-bed posture classification and limb identification
TLDR
An algorithm that uses pressure image data to detect a person's sleeping posture and identifies different body limbs and can be used in monitoring bed-bound patients and assessing the risk of pressure ulceration is proposed. Expand
A Posture Scheduling Algorithm Using Constrained Shortest Path to Prevent Pressure Ulcers
TLDR
An efficient algorithm to find a repositioning schedule for bed-bound patients based on their risk of ulcer development is presented, which minimizes the overall cost of nursing staff involvement in repositioned the patients while simultaneously decreases the chance of pressure ulcer formation. Expand
...
1
2
...