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

• Published in: Artificial Intelligence XXXV Vol. 11311; pp. 204 - 209
• Main Authors: Vox, Jan P., Wallhoff, Frank
• Format: Book Chapter
• Language: English
• Published: Switzerland Springer International Publishing AG 2018; Springer International Publishing
• Series: Lecture Notes in Computer Science
• Subjects: 3D-skeleton-data; Human motion recognition; Neural networks
• ISBN: 9783030041908; 3030041905
• ISSN: 0302-9743; 1611-3349
• DOI: 10.1007/978-3-030-04191-5_19

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.