We’ve detected that you are using an outdated browser. This will prevent you from accessing certain features. Update browser


AI-driven real-time error detection

Construction worker on scaffolding

The Challenge

Currently the process infrastructure builders and operators use to document work done on an asset is quite manual and retrospective, requiring a fitter to use a mobile device take photographs of their daily work on a site, a case handler to review and spot check the reported photos and flag errors such as jobs left incomplete or not done correctly, and a worker to go out to “fix” the potentially hazardous errors.

This challenge, set in conjunction with Infratek, sought innovative proposals for solutions that can harness the capabilities of computer vision, artificial intelligence and machine learning to not only improve how quickly errors are spotted in work on infrastructure assets, but to go further to offer real-time detection and feedback to the worker prior to leaving site to ensure the job is done right the first time, and improve safety for the worker and third parties.

The Finalists

The Winner

Infratrek chose Numberboost and their interactive visualisation and data analytics solution as the winner of this challenge. NumberBoost builds custom solutions using cutting-edge machine learning algorithms to solve a variety of real-world prediction and computer perception problems. 

Case Study

Check out the case study and find out how Infratek and NumberBoost worked together to tackle this challenge.

Start-up NumberBoost talks about their journey with the Safety Accelerator

More Info

Abstract image of flowing blue light streams

The Safetytech Report

Lloyd’s Register Foundation's new research forecasts that the combined global industry potential for the emerging safetytech market could grow to $863bn within three years.

Download the report now.
Can't find what you are looking for?

Hit enter or the arrow to search Hit enter to search

Search icon

Are you looking for?