A GENERIC COMPUTER VISION TOOL FOR RECOGNISING HUMAN ACTIVITIES

Authors

  • Jacobus Jacobs 1 Stellenbosch Unit for Operations Research in Engineering, Department of Industrial Engineering, Stellenbosch University, Stellenbosch, South Africa https://orcid.org/0000-0002-8583-7277
  • Stephan Nel 1 Stellenbosch Unit for Operations Research in Engineering, Department of Industrial Engineering, Stellenbosch University, Stellenbosch, South Africa https://orcid.org/0000-0002-0293-1234

DOI:

https://doi.org/10.7166/34-3-2956

Abstract

A prominent application area in the domain of computer vision is human activity recognition, which involves automatically detecting people’s actions from video footage. In this paper, a generic decision support tool capable of performing human activity recognition by employing computer vision is developed. The objective of the decision support tool is to facilitate the analysis of video footage by learning to identify human activities from video footage. The decision support tool facilitates the processing of raw data, the training of a computer vision model in respect of the processed data, and the deployment of the trained computer vision model in respect of unseen video footage. This paper details a computerised implementation of the decision support tool in respect of a benchmark data set and real-world data set involving the cash replenishment process of a South African bank.

Downloads

Download data is not yet available.

Downloads

Published

2023-11-17

How to Cite

Jacobs, J., & Nel, S. (2023). A GENERIC COMPUTER VISION TOOL FOR RECOGNISING HUMAN ACTIVITIES. The South African Journal of Industrial Engineering, 34(3), 336–355. https://doi.org/10.7166/34-3-2956

Issue

Vol. 34 No. 3 (2023)

Section

Special Edition

License

Authors who publish in the Journal agree to the following terms:
  1. Authors retain copyright and grant the Journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this Journal.
  2. Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the Journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this Journal.