Case Study: Engineering News-Record achieves faster, more accurate construction photo safety screening with Smartvid.io

A Case Study on Using Computer Vision for Safety Screening In Enr’s Annual Photo Competition

Engineering News-Record faced the challenge of quickly and accurately screening thousands of photo contest submissions for construction safety risks—identifying images with people and spotting missing personal protective equipment—without overburdening human reviewers. To help, they partnered with Smartvid.io and its VINNIE machine‑learning engine on the Smartvid.io media management platform to automate image and audio analysis for industrial photo libraries.

Smartvid.io’s VINNIE automatically scanned all 1,080 contest images in under 10 minutes (versus 4.5 hours for human reviewers), correctly detecting 446 images with people (humans found 414) and flagging 32 images missing hard hats and 106 missing safety vests. The Smartvid.io solution delivered faster, broader coverage and improved accuracy for safety screening, and can integrate with systems like Procore and BIM 360 Field to extend VINNIE’s automated monitoring across project photo and video archives.

Engineering News-Record