Depth-Camera-Based Under-Blanket Sleep Posture Classification Using Anatomical Landmark-Guided Deep Learning Model
- PMID: 36294072
- PMCID: PMC9603239
- DOI: 10.3390/ijerph192013491
Depth-Camera-Based Under-Blanket Sleep Posture Classification Using Anatomical Landmark-Guided Deep Learning Model
Abstract
Emerging sleep health technologies will have an impact on monitoring patients with sleep disorders. This study proposes a new deep learning model architecture that improves the under-blanket sleep posture classification accuracy by leveraging the anatomical landmark feature through an attention strategy. The system used an integrated visible light and depth camera. Deep learning models (ResNet-34, EfficientNet B4, and ECA-Net50) were trained using depth images. We compared the models with and without an anatomical landmark coordinate input generated with an open-source pose estimation model using visible image data. We recruited 120 participants to perform seven major sleep postures, namely, the supine posture, prone postures with the head turned left and right, left- and right-sided log postures, and left- and right-sided fetal postures under four blanket conditions, including no blanket, thin, medium, and thick. A data augmentation technique was applied to the blanket conditions. The data were sliced at an 8:2 training-to-testing ratio. The results showed that ECA-Net50 produced the best classification results. Incorporating the anatomical landmark features increased the F1 score of ECA-Net50 from 87.4% to 92.2%. Our findings also suggested that the classification performances of deep learning models guided with features of anatomical landmarks were less affected by the interference of blanket conditions.
Keywords: digital health; sleep behavior; sleep monitoring; sleep posture recognition; sleep surveillance; ubiquitous health.
Conflict of interest statement
The authors declare no conflict of interest. The funders had no role in the design of the study; in the collection, analyses, or interpretation of data; in the writing of the manuscript, or in the decision to publish the results.
Figures
![Figure 1](https://cdn.statically.io/img/www.ncbi.nlm.nih.gov/pmc/articles/instance/9603239/bin/ijerph-19-13491-g001.gif)
![Figure 2](https://cdn.statically.io/img/www.ncbi.nlm.nih.gov/pmc/articles/instance/9603239/bin/ijerph-19-13491-g002.gif)
![Figure 3](https://cdn.statically.io/img/www.ncbi.nlm.nih.gov/pmc/articles/instance/9603239/bin/ijerph-19-13491-g003.gif)
![Figure 4](https://cdn.statically.io/img/www.ncbi.nlm.nih.gov/pmc/articles/instance/9603239/bin/ijerph-19-13491-g004.gif)
Similar articles
-
Vision Transformers (ViT) for Blanket-Penetrating Sleep Posture Recognition Using a Triple Ultra-Wideband (UWB) Radar System.Sensors (Basel). 2023 Feb 23;23(5):2475. doi: 10.3390/s23052475. Sensors (Basel). 2023. PMID: 36904678 Free PMC article.
-
A Blanket Accommodative Sleep Posture Classification System Using an Infrared Depth Camera: A Deep Learning Approach with Synthetic Augmentation of Blanket Conditions.Sensors (Basel). 2021 Aug 18;21(16):5553. doi: 10.3390/s21165553. Sensors (Basel). 2021. PMID: 34450994 Free PMC article.
-
Two-Step Deep Learning for Estimating Human Sleep Pose Occluded by Bed Covers.Annu Int Conf IEEE Eng Med Biol Soc. 2019 Jul;2019:3115-3118. doi: 10.1109/EMBC.2019.8856873. Annu Int Conf IEEE Eng Med Biol Soc. 2019. PMID: 31946547
-
A Vision-Based System for In-Sleep Upper-Body and Head Pose Classification.Sensors (Basel). 2022 Mar 4;22(5):2014. doi: 10.3390/s22052014. Sensors (Basel). 2022. PMID: 35271162 Free PMC article.
-
Transfer Learning for Clinical Sleep Pose Detection Using a Single 2D IR Camera.IEEE Trans Neural Syst Rehabil Eng. 2021;29:290-299. doi: 10.1109/TNSRE.2020.3048121. Epub 2021 Mar 1. IEEE Trans Neural Syst Rehabil Eng. 2021. PMID: 33378261
Cited by
-
Assessing Non-Specific Neck Pain through Pose Estimation from Images Based on Ensemble Learning.Life (Basel). 2023 Nov 30;13(12):2292. doi: 10.3390/life13122292. Life (Basel). 2023. PMID: 38137893 Free PMC article.
-
Vision Transformers (ViT) for Blanket-Penetrating Sleep Posture Recognition Using a Triple Ultra-Wideband (UWB) Radar System.Sensors (Basel). 2023 Feb 23;23(5):2475. doi: 10.3390/s23052475. Sensors (Basel). 2023. PMID: 36904678 Free PMC article.
References
-
- Devaraj D., Devaraj U., Venkatnarayan K., Veluthat C., Ramachandran P., D’Souza G., Maheswari K.U. Prevalence of sleep practices, circadian types and their effect on sleep beliefs in general population: Knowledge and Beliefs About Sleep and Sleep Practices (KNOBS Survey) Sleep Vigil. 2021;5:61–69. doi: 10.1007/s41782-021-00128-6. - DOI
Publication types
MeSH terms
Grants and funding
LinkOut - more resources
Full Text Sources
Medical