A Vision-Based System for In-Sleep Upper-Body and Head Pose Classification.

Yan-Ying Li,Yi-Ping Hung,Shoue-Jen Wang

doi:10.3390/s22052014

Yan-Ying Li, Yi-Ping Hung + Show 1 more

Open Access

https://doi.org/10.3390/s22052014

Copy DOI

Abstract

Sleep quality is known to have a considerable impact on human health. Recent research shows that head and body pose play a vital role in affecting sleep quality. This paper presents a deep multi-task learning network to perform head and upper-body detection and pose classification during sleep. The proposed system has two major advantages: first, it detects and predicts upper-body pose and head pose simultaneously during sleep, and second, it is a contact-free home security camera-based monitoring system that can work on remote subjects, as it uses images captured by a home security camera. In addition, a synopsis of sleep postures is provided for analysis and diagnosis of sleep patterns. Experimental results show that our multi-task model achieves an average of 92.5% accuracy on challenging datasets, yields the best performance compared to the other methods, and obtains 91.7% accuracy on the real-life overnight sleep data. The proposed system can be applied reliably to extensive public sleep data with various covering conditions and is robust to real-life overnight sleep data.

Highlights

Good sleep quality helps the mind and body remain healthy
A contact-free sleep monitoring system is necessary for healthcare in the non-contact era
The SimultaneouslyCollected Multimodal Lying Pose (SLP) dataset [42] with annotated head and upper-body position was used for training and testing

Summary

Introduction

Good sleep quality helps the mind and body remain healthy. Monitoring in-bed postures provides valuable information regarding the intensity of dreams [3], risk of pressure ulcers [4], patients’ mobility [5], obstructive sleep apnea syndrome [6], risk of spinal symptoms [7], and quality of sleep [8]. Sleep behavior monitoring is a critical aspect of healthcare management. Home sleep testing is becoming critical at present owing to the overwhelmed healthcare system resulting from the COVID-19 pandemic [9]. A contact-free sleep monitoring system is necessary for healthcare in the non-contact era. The ViBe a rapid background modeling technique for video plied to reduce processing. TheisViBe is a rapid background modeling technique for sequences. The method is robustisand efficient for natural scenes. The method robust and efficient forbackground natural background scenes

Methods

Results

Discussion

Conclusion