id	author	title	date	pages	extension	mime	words	sentences	flesch	summary	cache	txt
work_qxvnriwsrjgqnj45s4f47lnzca	Audrius Kulikajevas	Detection of sitting posture using hierarchical image composition and deep learning	2021	20	.pdf	application/pdf	8963	1081	56	accuracy at 10 fps rate for sitting posture recognition. Keywords Posture detection, Computer vision, Deep learning, Artificial neural network, network approach for tracking human posture in home office environments, where solution to this problem is skeleton based posture recognition (Jiang et al., 2015) using (2019) exploit Deep CNNs based on the DenseNet model to learn directly an end-toend mapping between the input skeleton sequences and their action label for human Such position would cause other known skeleton-based posture prediction methods to fail, Table 1 Layers of the proposed neural network architecture for human posture recognition. Figure 3 Activity diagram of the proposed method for sitting posture state recognition. Our method allows to achieve the real time sitting posture recognition with the same or Human posture recognition based on Detection of sitting posture using hierarchical image composition and deep learning Detection of sitting posture using hierarchical image composition and deep learning	./cache/work_qxvnriwsrjgqnj45s4f47lnzca.pdf	./txt/work_qxvnriwsrjgqnj45s4f47lnzca.txt