Detection of sitting posture using hierarchical image composition and deep learning

Audrius Kulikajevas; Rytis Maskeliunas; Robertas Damaševičius

doi:10.7717/peerj-cs.442

Detection of sitting posture using hierarchical image composition and deep learning

PeerJ Comput Sci. 2021 Mar 23:7:e442. doi: 10.7717/peerj-cs.442. eCollection 2021.

Authors

Audrius Kulikajevas¹, Rytis Maskeliunas¹, Robertas Damaševičius^{2

3}

Affiliations

¹ Department of Multimedia Engineering, Kaunas University of Technology, Kaunas, Lithuania.
² Department of Applied Informatics, Vytautas Magnus University, Kaunas, Lithuania.
³ Faculty of Applied Mathematics, Silesian University of Technology, Gliwice, Poland.

Abstract

Human posture detection allows the capture of the kinematic parameters of the human body, which is important for many applications, such as assisted living, healthcare, physical exercising and rehabilitation. This task can greatly benefit from recent development in deep learning and computer vision. In this paper, we propose a novel deep recurrent hierarchical network (DRHN) model based on MobileNetV2 that allows for greater flexibility by reducing or eliminating posture detection problems related to a limited visibility human torso in the frame, i.e., the occlusion problem. The DRHN network accepts the RGB-Depth frame sequences and produces a representation of semantically related posture states. We achieved 91.47% accuracy at 10 fps rate for sitting posture recognition.

Keywords: Artificial neural network; Computer vision; Deep learning; Depth sensors; Posture detection; Sitting posture; e-Health.

Grants and funding

The authors received no funding for this work.