A semiconductor manufacturer wanted cameras watching every chamber on its lines: 25 cameras per chamber, 40 chambers per site. Nobody can watch a thousand feeds, and sending them all to the cloud would have been slow, expensive and a risk for sensitive footage. They had only a couple of dozen labelled images to start from. We proved the approach in an MVP on their own footage, analysing more than 300 frames per second on site, then designed the site so the vision AI runs next to the cameras, every feed is checked as it arrives, and the video stays in the building.
| Client | Semiconductor manufacturer (name withheld) |
| Problem | Cameras on every chamber, but no way to watch or act on a thousand feeds in time |
| Starting point | About 25 labelled images and a few videos |
| Scope | 25 cameras per chamber · 40 chambers per site · about 21 TB of video a month |
| Deployment | On site, next to the cameras, on NVIDIA Jetson hardware accelerators. No cloud in the decision path |
| Engagement | MVP on the customer's own footage, then a site design sized from the MVP results |
| MVP result | 300+ frames per second analysed on site, on the customer's own footage |
Cameras get installed for safety and quality, then mostly record. Problems are found later, on a replay, after the parts are scrapped.
A round trip to the cloud adds delay and depends on the network link. A decision that matters on the line can't wait for either.
Per-camera cloud pricing looks small at ten cameras. At a thousand, it becomes one of the biggest lines in the budget.
Lighting, fixtures and products change. A model set up once and left alone gets worse every month.
Each feed is checked as it arrives, on hardware in the customer's building. No cloud round trip, and it keeps working if the internet link drops.
Every flag comes with the frame and a short note on what was seen, sent to the operator or engineer who owns that chamber.
The system flags and asks. It never moves equipment. The customer's control systems and people decide what happens next.
Starting from about 25 labelled images, we built the first models and look after them from there. Improvements are tested on the customer's own footage before they go live, and can be rolled back.
| Cameras | Rugged industrial cameras, made in the USA and NDAA compliant, with depth sensing and night vision. Existing cameras can be used too. |
| On-site AI hardware | Unovie's custom-built NVIDIA Jetson hardware accelerators, sized to the site's camera count. Keeps running if one unit fails. |
| Video stays on site | Footage is analysed and kept on site. Archiving it anywhere else is the customer's choice, not a requirement. |
| Connected to existing systems | Flags go to the existing alarms, MES, quality and work-order systems. |
| Looked after | Model updates, hardware support and monitoring included. Buy the hardware or take it as a service. |
This project was in a chip fab. The same engine is set up for other lines during a pilot, on their own footage.
Watches a test run alongside the sensors and flags anything unusual to the test conductor as it happens.
Checks welds and tab alignment in line, together with the process signals for the same cell.
Spots misplaced parts and drifting motions before they turn into scrap or a stopped cell.
Watches jams, spills and blocked lanes on conveyors and loading docks and alerts the shift lead.
| Step | What happens |
|---|---|
| Site audit | No charge, 1–2 days. An engineer walks your floor, looks at your cameras and network, and picks the first tools to watch. |
| 6-week pilot | A handful of cameras on one tool, on your own footage, with a results report you can check. |
| Production | Roll out chamber by chamber, then site by site, in about a quarter. |
Customer details are withheld under confidentiality. The 300+ frames per second was measured in the MVP on the customer's own footage. Camera, chamber and video figures are the customer's site requirements.
Book a short live demo. We'll show the vision engine checking a camera feed on site, and talk through what it would watch on your floor.