Preprocessing and Normalization of 3D-Skeleton-Data for Human Motion Recognition

• Published in: 2018 IEEE Life Sciences Conference (LSC) pp. 279 - 282
• Main Authors: Vox, Jan P., Wallhoff, Frank
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.10.2018
• Subjects: 3D-skeleton-data; Accuracy; Data preprocessing; Human activity recognition; Human motion recognition; Life sciences; Machine learning algorithms; normalization; preprocessing; Shape; support vector machine; Support vector machines

One key task for motion recognition using machine learning algorithms is the preprocessing of the input data. In this work 3D-skeleton-data is used to classify 19 motion exercises. Due to different body shapes and deviations in the movements from different subjects it becomes necessary to normalize...