Li, Y.-Y.Y.-Y.LiLei, Y.-J.Y.-J.LeiChen, L.C.-L.L.C.-L.ChenYI-PING HUNG2020-06-112020-06-112018https://scholars.lib.ntu.edu.tw/handle/123456789/500493https://www.scopus.com/inward/record.uri?eid=2-s2.0-85048786870&doi=10.1109%2fIWAIT.2018.8369761&partnerID=40&md5=e556fbe83080ae57da8232567af1148fSleep posture is closely related to sleep quality. Moreover, several studies reveal that an incorrect sleep position can result in physical pain. A non-invasive image-based method was proposed for identifying ten sleep postures with high accuracy. The positions of the legs and arms was considered and more complex but common sleep postures was classified, such as fatal left, yearner left, log left, fatal right, yearner right, log right, soldier down, faller down, soldier up, faller up. Input of depth images were preprocessed and a deep multi-stream convolutional neural network was adopted for classification. The work is available for natural scenarios in which people sleep with blanket or quilt covering. Finally, 22 subjects were participated for recording depth images of 10 types of sleep postures, and efficiency of the network was also evaluated. © 2018 IEEE.Depth Image; Multi-Stream CNN; Sleep Posture ClassificationNeural networks; Convolutional neural network; Depth image; Image-based methods; Multi-stream; Posture classification; Recording depth; Sleep quality; Vertical distances; Sleep researchconference paper10.1109/IWAIT.2018.83697612-s2.0-85048786870