Skip to content

Blackbook.ai

PPE Detection

Timelapse delivers a premium service offering time-lapse photographers from bespoke hardware to internal data management cleared for defense contracts. Their technology allows customers to clearly see what is happening on site, allowing them to monitor progress from their office or anywhere else in the world. This visual record of their customers' projects helps customers improve processes, monitor OH&S compliance and provides an invaluable record for dispute resolution.

Client Industry

Photography & Recording

Technology stack

Computer Vision

Industry

Photography & Recording

Technology stack

Computer Vision

Industry

Photography & Recording

Technology stack

Computer Vision

The challenge

Timelapse produces a significant amount of photography data as part of their Cloud Render product. They wanted to offer their customers a way to help monitor their OH&S compliance without the cumbersome task of humans having to review the photography in entirety.  

Timelapse customers often need capability to monitor safety violations for: 

  • Employee Safety – ensure employees are operating safely 
  • Marketing – ensure any footage intended for public release does not contain violations 
  • Legal – ensure that sites are not breaching OSHA standards

The solution

Blackbook was engaged by Timelapse to design, build and deploy a computer vision model capable of detecting OH&S breaches in their photography data.  

A Web Portal and custom AI object detection model was built on AWS cloud infrastructure, which together would assist with the safety review process. Note that a separate Web Portal with custom DNS was provided to each Timelapse customer as required. 

The AI computer vision model was trained to detect the absence of Hard Hats and Safety Vests, as well as the capability to detect social distancing violations (removed once COVID-19 restrictions were lifted). 

The Web Portal facilitates the submission of the Timelapse imagery for AI analysis. Once the imagery has been analysed, any resulting AI detections will be followed by a human-in-the-loop review. This stage allows for invalid detections to be deleted and any new detections to be created using an embedded annotation tool. Any corrections are captured for potential future stages of model retraining.

The outcomes

The model achieved over 70% accuracy on the limited initial dataset with strong improvements with data diversification with Australian workwear data and model retraining through Web Portal use. The Web Portal and model are actively being used by Timelapse customers, with potential for product expansion.

Related case studies

Beef Sales Assistant Chat Bot

The customer is a premium beef producer with an experienced sales team servicing foodservice, retail, and export customers. Sales representatives manage a wide range of cuts, specifications, pricing rules, and inventory positions while responding quickly to customer requests.

Read more >

Marble and Weight Prediction

The customer is a large beef producer managing complex supply chains from livestock intake through to sales and financial planning. Accurate forecasts of marbling scores and carcass weights are essential for pricing, customer commitments, and financial performance.

Read more >

Carcass Data Analytics Platform

The customer is Australia’s largest integrated cattle and beef producer, supplying premium grass-fed, grain-fed, and Wagyu beef to global export markets. Their operations span backgrounding, feedlots, processing, and commercial functions, operating at significant scale with a strong focus on high-quality, data-driven production.

Read more >
Services
About