Human Motion Recognition Using 3D-Skeleton-Data and Neural Networks

Autor:	Frank Wallhoff, Jan P. Vox
Rok vydání:	2018
Předmět:	Artificial neural network Computer science business.industry Work (physics) Pattern recognition Artificial intelligence Skeleton (category theory) Human motion business Motion (physics) Backpropagation
Zdroj:	Lecture Notes in Computer Science ISBN: 9783030041908 SGAI Conf.
DOI:	10.1007/978-3-030-04191-5_19
Popis:	This work addresses the recognition of human motion exercises using 3D-skeleton-data and Neural Networks (NN). The examined dataset contains 16 gymnastic motion exercises (e.g. squats, lunges) executed from 21 subjects and captured with the second version of the MicrosoftTM Kinect sensor (Kinect v2). The NN was trained with eight datasets from eight subjects and tested with 13 unknown datasets. The investigation in this work focuses on the configuration of NNs for human motion recognition. The authors will conclude that a backpropagation NN consisting of 100 neurons, three hidden layers, and a learning rate of 0.001 reaches the best accuracy with 93.8% correct.
Databáze:	OpenAIRE
Externí odkaz:	https://explore.openaire.eu/search/publication?articleId=doi_________::514312d531d5e07753f0816638cf182f https://doi.org/10.1007/978-3-030-04191-5_19 Zobrazit plný text záznamu