As recent advances in AI-based visual identification have progressed, job site monitoring provider Earthcam has been looking to bring these features to its extensive camera network.
Now, as AI technology continues to advance in sophistication, the company has moved beyond safety-related AI visual detection into active tracking of material deliveries and installations.
“The monitoring of the materials [feature] It’s been in beta for a year, we just announced it at [Procore] Groundbreak,” explains Brian Cury, CEO of Earthcam. The system has been trained with Earthcam’s own footage from its countless job site cameras and has integrations with Procore and Autodesk software to update project progress in function of programming tasks based on the analysis of Earthcam materials.

“We like to say we’re not in the camera business, we’re in the software business,” says Cury. “We’re taking equipment and material deliveries to the job site, then sending them to Procore, putting it against the schedule with images,” he explains.
Alerts can be automatically generated when materials arrive on site, with a photo automatically attached. “So let’s say the HVAC ducts are delivered, here’s a picture of the delivery. It’s these visual cue sources of truth that make the difference.”

Cury sees increased use of visual detection AI as a key way to compensate for deficiencies in the current state of construction scheduling.
“Times have been getting longer since the pandemic and the industry is trying to get it back in line,” he says. “But people don’t communicate. The electrician shows up with his crew and the chip job isn’t done yet, so they might not show up for weeks after it’s done. So we’ve moved on towards alerts and color coding to help things along.”
Automatic color coding of materials, as well as installation progress tracking, has been a requested feature according to Cury, citing many homeowners and developers who have turned to Earthcam and other camera systems to monitor construction sites. remote work in recent years. But manually examining video footage to determine what work has been done takes time and is a natural fit for AI automation, he says.
Another unexpectedly popular feature has been using visual AI to track how full trash cans are on job sites, helping to schedule quick removal of construction waste. “A bin full of trash on the weekend is a fire hazard,” Cury notes, “so we know if it’s full or empty with AI.”
Improve site security with AI
While material and job tracking use cloud-based systems and focus on broader software integrations, Earthcam has also continued to develop on-board camera AI processing for instant safety alerts.
The company offers cameras with built-in AI analytics to flag safety violations, including lack of PPE, fall hazards or unsafe use of equipment. In addition to spotting common hazards such as spills or when someone gets too close to active equipment, visual AI can also tag workers working at height and assess whether they are properly strapped down.

William Sharp, Earthcam’s vice president of product development, says edge detection for the work-at-height feature was complicated programming. “We’ve reached where we can collect [workers] on roofs, scaffolding, elevators, height verification works there too.”
This was a challenge since these are static cameras placed at odd angles, but Earthcam’s visual processing has reached the point where edge detection is fairly consistent regardless of complex visual geometry, Sharp says. “I’ve been doing it for a long time, every time we have a new challenge, we’ve been able to solve them. As challenges arise. we will continue to solve them”.