Marian-Leontin Pop
Technical University of Cluj-Napoca

Szilard Molnar
Technical University of Cluj-Napoca

Alexandru Pop
Technical University of Cluj-Napoca

Benjamin Kelenyi
Technical University of Cluj-Napoca

Levente Tamas
Technical University of Cluj-Napoca

Andrei Cozma
Analog Devices International

Abstract

In this paper a Time of Flight (ToF) camera specific data processing pipeline is presented, followed by real life applications using artificial intelligence. These applications include use cases such as gesture recognition, movement direction estimation or physical exercises monitoring. The whole pipeline for the body pose estimation is described in details, starting from generating and training phases to the pose estimation and deployment. The final deployment targets were Nvidia Xavier NX and AGX platforms receiving data from an Analog Devices ToF camera.

Keywords

transfer learning, ToF, python

DOI

10.25080/majora-1b6fd038-013

Bibtex entry

Full text PDF

Copyright © 2021 Marian-Leontin Pop et al. This is an open-access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.