Multi-Speaker Tracking from Azure Kinect: Performance Evaluation using Generalized Optimal Sub-Pattern Assignment

Authors

  • Muhammad Atiff Zakwan Bin Mohd Ariffin Universiti Teknologi Malaysia
  • Siti Nur Aisyah Binti Mohd Robi Universiti Teknologi Malaysia
  • Mohd Azri Bin Mohd Izhar Universiti Teknologi Malaysia
  • Norulhusna Binti Ahmad Universiti Teknologi Malaysia

DOI:

https://doi.org/10.11113/oiji2023.11n2.289

Keywords:

Multi-speaker tracking, Azure Kinect device, optimal sub-pattern assignment, body tracking, performance evaluation

Abstract

The software and the hardware features of Azure Kinect show the potential for its application in multiple speaker tracking. We then evaluate the system’s capabilities by conducting tests using our given setup, including various scenarios to evaluate its tracking performance. The tracking performance is calculated using generalized optimal sub-pattern assignment (GOSPA) and multiple objects tracking accuracy (MOTA) metrics. It has been found that the body tracking algorithm can perform well in certain multi-speaker tracking conditions.

Downloads

Published

2023-12-18

How to Cite

Bin Mohd Ariffin, M. A. Z., Binti Mohd Robi, S. N. A., Bin Mohd Izhar, M. A., & Binti Ahmad, N. (2023). Multi-Speaker Tracking from Azure Kinect: Performance Evaluation using Generalized Optimal Sub-Pattern Assignment. Open International Journal of Informatics, 11(2), 188–195. https://doi.org/10.11113/oiji2023.11n2.289

Issue

Vol. 11 No. 2 (2023): Open International Journal of Informatics (OIJI)

Section

Articles