Nonintrusive Fine-Grained Home Care Monitoring: Characterizing Quality of In-Home Postural Changes Using Bone-Based Human Sensing

Abstract

In contrast to the physical activities of able-bodied people at home, most people who require long-term specific care (e.g., bedridden patients and patients who have difficulty walking) usually show more low-intensity slow physical activities with postural changes. Although the existing devices can detect data such as heart rate and the number of steps, they have been increasing the physical burden relying on long-term wearing. The purpose of this paper is to realize a noninvasive fine-grained home care monitoring system that is sustainable for people requiring special care. In the proposed method, we present a novel technique that integrates inexpensive camera devices and bone-based human sensing technologies to characterize the quality of in-home postural changes. We realize a local process in feature data acquisition once per second, which extends from a computer browser to Raspberry Pi. Our key idea is to regard the changes of the bounding box output by standalone pose estimation models in the shape and distance as the quality of the pose conversion, body movement, and positional changes. Furthermore, we use multiple servers to realize distributed processing that uploads data to implement home monitoring as a web service. Based on the experimental results, we conveyed our findings and advice to the subject that include where the daily living habits and the irregularity of home care timings needed improvement.

Front-end deep learning web apps development and deployment: a review

“…MoveNet is a lightning-fast and highly accurate model that detects the body’s 17 key points; BlazePose can detect 33 keypoints, and PoseNet can detect multiple poses, each of which includes 17 key points. Works on Pose-detection can be found in [ 20 , 32 , 81 , 85 , 92 , 96 , 96 , 98 , 106 , 116 , 124 ] BodyPix This is a body segmentation model that segments 24 body components from a background image or video in real-time, and it also works for multiple people. Its design is based on either MobileNetV1, a smaller but less precise model, or ResNet50, a bigger but more precise model.…”

“…Another repository that is linked to their framework includes the PyTorch Hub, 19 which presently includes packages that may be accessed through the PyTorch framework's APIs. Other such repositories include Microsoft cognitive toolkit, 20 Caffe/Caffe2 model zoo, 21 and MXNet model zoo. 22 Two repositories that are not connected to any specific framework are Model Zoo 23 and ModelHub.…”

“…Rehabilitation and monitoring To facilitate fall risk assessment and rehabilitation monitoring for the elderly, a web app was introduced in [98]. A similar home care monitoring system was reported in [20], where it can assess the quality of in-home postural alterations, such as posture conversion, body movement, and positional changes.…”

An Efficient Approach Using Knowledge Distillation Methods to Stabilize Performance in a Lightweight Top-Down Posture Estimation Network

“…Recently, multi-person pose estimation has drawn increasing attention because of its applicability in real-life applications, such as postural correction [28], action recognition [29], and health care [30]. Multi-person pose estimation using neural networks can be determined via two main approaches.…”

Assisting Personalized Healthcare of Elderly People: Developing a Rule-Based Virtual Caregiver System Using Mobile Chatbot

“…In the personalized healthcare of the elderly using machines (i.e., smart healthcare), it often needs two parts of work for elderly people, including situational recognition and care nursing intervention. Studies of situation recognition include in-home fine-grained scenes (i.e., called context ) recognition [ 10 , 11 , 12 ]), nonintrusive quality characterization of postural changes [ 13 ], and user-defined indoor location sensing [ 14 ]. As for care nursing intervention, it is common to use physical care robots [ 15 , 16 , 17 , 18 ], chatbots [ 19 , 20 , 21 ], and virtual agents [ 22 , 23 , 24 , 25 , 26 ].…”