Implementation of Artificial Intelligence to Monitor PPE on Site

John Sisk has a primary focus on health and safety across all construction sites; “Zero Incidents, Zero Injuries” is the core ethos of our site activities.

With the aim to improve the H&S on our site, we have been piloting the implementation of an artificial intelligence powered image recognition system. This system is installed into an existing CCTV system that samples operative compliance in wearing four of the five mandatory five-part PPE on site (hi-viz, hard hat, gloves and glasses).

How It Works:

The system works by using machine ‘deep learning’ to perform near-real time analysis on photos which are automatically uploaded to the cloud platform. It then identifies any workers who are not conforming to the PPE regulations with no human input. In order for the AI to ‘learn’ how to identify these issues, limited human reviews of the programme need to occur to ensure accurate results are given.


The systems main purpose is not to punish people who are not wearing the correct PPE, but to increase the level and awareness of H&S on site to create the safest possible work environment for everyone at Sisk. Another main reason for the implementation of this system was to completely eliminate the human input freeing up time for staff to focus other key areas of health and safety. This system provides the users with a greatly approved analysis of the construction site risk analysis highlighting best practice and where improvements can be made site-wide.

Benefits include:

  • Improve visibility to all job sites;
  • Remotely inspect safety hazards and company policies including PPE compliance policies and critical practices such as housekeeping and the use of ladders, etc.

Footer Reference

Entry submitted by John Sisk & Son

Did you find this article helpful?

Please rate this article

0 votes, average: 0.00 out of 50 votes, average: 0.00 out of 50 votes, average: 0.00 out of 50 votes, average: 0.00 out of 50 votes, average: 0.00 out of 5 (0 votes, average: 0.00 out of 5)
You need to be a registered member to rate this.

Leave a comment

Return to previous page

The Scheme does not promote or endorse any products, goods or services. For more information, click here.