Detection of Sitting Posture Using Hierarchical Image Composition and Deep Learning
Overview
Affiliations
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 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.
Exploiting the features of deep residual network with SVM classifier for human posture recognition.
Kareem I, Ali S, Bilal M, Hanif M PLoS One. 2024; 19(12):e0314959.
PMID: 39636954 PMC: 11620452. DOI: 10.1371/journal.pone.0314959.
A fine-tuned YOLOv5 deep learning approach for real-time house number detection.
Tasyurek M, Ozturk C PeerJ Comput Sci. 2023; 9:e1453.
PMID: 37547390 PMC: 10403189. DOI: 10.7717/peerj-cs.1453.
Posture monitoring in healthcare: a systematic mapping study and taxonomy.
Camboim B, da Rosa Tavares J, Tavares M, Barbosa J Med Biol Eng Comput. 2023; 61(8):1887-1899.
PMID: 37347401 DOI: 10.1007/s11517-023-02851-w.
Qi J, Li D, He J, Wang Y Sensors (Basel). 2023; 23(7).
PMID: 37050699 PMC: 10098931. DOI: 10.3390/s23073639.
YoNet: A Neural Network for Yoga Pose Classification.
Ashraf F, Islam M, Kabir M, Uddin J SN Comput Sci. 2023; 4(2):198.
PMID: 36785804 PMC: 9907194. DOI: 10.1007/s42979-022-01618-8.