Two-Step Deep Learning for Estimating Human Sleep Pose Occluded by Bed Covers
Two-Step Deep Learning for Estimating Human Sleep Pose Occluded by Bed Covers
复制标题
用于估计被床罩遮挡的人体睡眠姿势的两步深度学习
DOI：
10.1109/embc.2019.8856873
复制
发表时间：
2019
期刊：
影响因子：
--
通讯作者：
K. Wells
中科院分区：
文献类型：
--
作者：
S. Mohammadi;S. Kouchaki;Sofia Khan;D. Dijk;A. Hilton;K. Wells
在这项研究中，提出了一种新的睡眠姿势识别方法，使用两步深度学习过程对12种不同的睡眠姿势进行分类。为此，迁移学习作为初始阶段重新训练了一个著名的CNN网络（VGG-19），将数据分类为四个主要的姿势类别，即：仰卧、左、右和俯卧。根据VGG-19做出的决定，图像数据的子集接下来被传递到四个专用子类CNN之一。结果，姿势估计标签从四个睡眠姿势标签之一进一步细化为12个睡眠姿势标签之一。10名参与者记录了12个预定义睡眠姿势的红外（IR）图像。参与者被毯子覆盖以遮挡原始姿势并呈现更真实的睡眠情况。最后，我们将我们的结果与（1）传统的CNN从头开始学习和（2）在一个阶段重新训练VGG-19网络进行了比较。平均准确率分别由（1）和（2）的74.5%和78.1%提高到85.6%。
In this study, a novel sleep pose identification method has been proposed for classifying 12 different sleep postures using a two-step deep learning process. For this purpose, transfer learning as an initial stage retrains a well-known CNN network (VGG-19) to categorise the data into four main pose classes, namely: supine, left, right, and prone. According to the decision made by VGG-19, subsets of the image data are next passed to one of four dedicated sub-class CNNs. As a result, the pose estimation label is further refined from one of four sleep pose labels to one of 12 sleep pose labels. 10 participants contributed for recording infrared (IR) images of 12 pre-defined sleep positions. Participants were covered by a blanket to occlude the original pose and present a more realistic sleep situation. Finally, we have compared our results with (1) the traditional CNN learning from scratch and (2) retrained VGG-19 network in one stage. The average accuracy increased from 74.5% & 78.1% to 85.6% compared with (1) & (2) respectively.