Skip to content
PRANINNOVATIONSProduction Specialists

Physical AI

Computer vision that runs where the cameras are

Vision systems that make a call in milliseconds, on hardware bolted to the line. Sending video to a data centre is too slow for a reject gate, too expensive at scale, and in plenty of buildings simply not allowed.

Arrange a site survey
Edge vision inspection: an overhead machine-vision camera on an articulated arm projects a light cone onto a machined part moving along a conveyor, with detected regions marked on the part

Inspection cell 01

Detection
99.4%
Latency
12 ms

One line, instrumented

01

What's already there

Cameras recording for insurance that nobody watches live. A historian holding six years of vibration readings. A quality sheet on paper that never reaches process engineering. Most of what a system needs is already on site. It just isn't connected to anything that can act.

02

Where it has to run

A reject gate has milliseconds. The footage isn't allowed to leave the building. The uplink will drop on the third shift. None of that is an edge case; it is the job, and it rules out anything that needs a round trip to a data centre.

03

What working means

Before any code, working becomes a number. Detection rate on a held-out set. Decision latency at the camera. Availability across sites. Written down, signed, and then measured in shadow mode before the system is allowed to act on anything.

04

What gets assembled

Five practices, one team.

  1. Vision on the line
  2. Devices that act on what they sense
  3. The interfaces into your controllers
  4. The product around it
  5. The system that holds all of it
05

And it keeps running

Products change. Lighting gets replaced. A camera moves during maintenance. Accuracy decays without announcing itself, so the loop comes back: monitored against sampled ground truth, retrained on a schedule, rolled out in waves.

What working means here

Signed first. Measured after.

The value of each one is set with you during scoping, from your data and your line. What does not change is that they are written down first and published against afterwards, pass or fail.

  1. 01

    Detection rate

    On a held-out set from your own footage, across shifts and changeovers

  2. 02

    Decision latency

    Frame in to signal out, on the device installed at the line

  3. 03

    False-positive rate

    Measured in shadow mode before the system is allowed to act

We publish the measurements behind this practice, including the runs that failed.

Vision Detection Deployment Benchmark 2026

How it is assembled

Stage by stage

Each one ends in something you keep.

  1. Step 01

    Site survey

    We come to the floor. Lighting, angles, optics, mounting, network and power are measured before anything is promised.

  2. Step 02

    Capture and annotate

    Real production recorded across shifts and changeovers, labelled against the classes your quality team already uses.

  3. Step 03

    Build and tune

    Model development and optimisation until it holds the required frame rate on the hardware being installed.

  4. Step 04

    Commission on the line

    Hardware mounted, integrated with the control system, running in shadow mode alongside your existing process.

  5. Step 05

    Shadow run and sign-off

    A monitored production period reviewed against the agreed thresholds before the system acts on its own.

Scope

What the work includes

  • Site survey: lighting, camera placement, optics, mounting, network and power
  • Data capture and annotation, including the failure modes that matter
  • Model development against your footage and your defect classes
  • Optimisation to hold the frame rate your process actually needs
  • Deployment to industrial edge hardware, sealed and mounted
  • Integration with reject mechanisms, HMIs and existing camera systems
  • Shadow-mode running before anything acts automatically
  • Drift monitoring and a scheduled retraining path

Deliverables

What you keep

  1. 01Site survey and camera plan
  2. 02Annotated dataset, owned by you
  3. 03Validated model with a published confusion matrix
  4. 04Commissioned edge hardware on the line
  5. 05Integration with your control system
  6. 06Shadow-run report and sign-off

Typical stack

PyTorch · ONNX Runtime · TensorRT · OpenCV · GStreamer · NVIDIA Jetson · GigE Vision / RTSP · OPC UA

Sizing

The shapes it comes in

Single station
One camera, one industrial edge unit
One inspection point, one defect family, one line
Line
Three to eight cameras with local aggregation
Full line coverage with shared reporting
Multi-site
Managed estate across plants
Central model management, staged rollout, per-site validation

Manufacturing · Vision

Surface defect inspection, decided at the camera in 12 ms

Final inspection was manual and sampled, so surface defects were being found by the customer rather than on the floor. We surveyed the cell, captured production across three shifts, and commissioned an edge vision station that inspects every part and drives the existing reject gate.

Read the engagement
12 ms
decision latency at the camera
99.4%
detection rate on hold-out set
100%
of parts inspected, up from sampled

Start

How Edge AI & Computer Vision begins

Vision system, single line or cell: $60K–150K

Where an engagement lands inside its band is set by data readiness, integration depth, the reliability bar, evaluation burden, deployment constraints and usage economics. All six, explained.

Thirty minutes on the problem and where it happens, then a fixed-price pilot if it looks like a fit.

Arrange a site survey

FAQ

Asked before signing

Only if you want it to. The default keeps frames on the edge device, sends structured results to your systems, and works with the site's uplink disconnected.

That depends on your parts, your defects and your lighting, which is why we will not quote a number before the survey. Send sample images and the Vision Feasibility Check gives you an accuracy band in writing, free.

Frequently. The survey covers whether existing optics and placement can hold the accuracy you need, and says plainly when they cannot.

New products and tooling changes shift the data. Engagements include a retraining path, and drift monitoring that flags a refresh before quality reports do.

Often paired with

Where this fits with the rest

  1. 01Physical AI

    Vision Systems Integration

    Cameras, optics, lighting, enclosures, and the PLC, SCADA and MES interfaces that make results act.

  2. 02Physical AI

    AI IoT Development

    Sensor fusion, predictive maintenance and condition monitoring across a fleet you can update.

  3. 03Start here

    Vision Feasibility Check

    Send 30–50 sample images. Get a written memo: accuracy band, hardware class, risks, go or no-go.