본문 바로가기
  • Home

Development of Workplace Risk Assessment System Based on AI Video Analysis

  • Journal of The Korea Society of Computer and Information
  • Abbr : JKSCI
  • 2024, 29(1), pp.151-161
  • DOI : 10.9708/jksci.2024.29.01.151
  • Publisher : The Korean Society Of Computer And Information
  • Research Area : Engineering > Computer Science
  • Received : December 19, 2023
  • Accepted : January 11, 2024
  • Published : January 31, 2024

Jeong-In Park 1

1유에프엠시스템즈(주)

Accredited

ABSTRACT

In this paper, we develop ‘the Danger Map’ of a workplace to identify risk and harmful factors by analyzing images of each process within the manufacturing plant site using artificial intelligence (AI). We proposed a system that automatically derives ‘the risk and safety levels’ based on the frequency and intensity derived from this Danger Map in accordance with actual field conditions and applies them to similar manufacturing industries. In particular, in the traditional evaluation method of manually evaluating the risk of a workplace using Excel, the risk level for each risk and harmful factor acquired from the video is automatically calculated and evaluated to ensure safety through the system and calculate the safety level, so that the company can take appropriate actions accordingly. and measures were prepared. To automate safety calculation and evaluation, 'Heinrich's law' was used as a model, and a 5X4 point evaluation scale was calculated for risky behavior patterns. To demonstrate this system, we applied it to a casting factory and were able to save 2 people the time and labor required to calculate safety each month.

Citation status

* References for papers published after 2023 are currently being built.