Skip to content
Contact Us
Start a Project info@nexlavision.com
Data & Prediction

Systems that see what nobody has time to watch

Cameras produce far more footage than anyone reviews. Computer vision turns that into counts, alerts and measurements — reliably, provided you are honest about lighting, angles and how often the model is allowed to be wrong.

Illustrative line inspection: a camera frame with detection boxes over three items, one flagged as a surface defect; inference runs on site and the defect is raised as an event for operator review.

The environment decides feasibility

The same detection task can be straightforward or impossible depending on lighting, camera placement and how much the scene varies. We assess the real environment before promising accuracy, and often the highest-value change is moving a camera rather than improving a model.

Close inspection of electronic components on a workbench
  1. 01

    Feasibility assessment

    We work from your actual footage, not a public benchmark, before committing to a target.

  2. 02

    Data collection and labelling

    Building a representative dataset including the awkward edge cases — normally the largest task.

  3. 03

    Edge or cloud decision

    Driven by bandwidth, latency and privacy. On-site processing is frequently the right answer.

  4. 04

    Accuracy targets

    Precision and recall agreed explicitly, because the cost of a false positive and a false negative are rarely equal.

What we build

01

Object detection and counting

Locate and count items, vehicles or people in image and video streams, with tracking across frames.

02

Quality inspection

Detect defects, missing components and tolerance breaches on a line, faster and more consistently than sampling by eye.

03

OCR and document capture

Read printed and handwritten text from photographs, forms, labels and plates under real-world conditions.

04

Video intelligence

Event detection across continuous streams — zone entry, dwell time, process timing — summarised rather than stored in full.

05

Safety and compliance monitoring

PPE checks, restricted-zone breaches and process adherence, with alerting rather than passive recording.

06

Edge deployment

Optimised models running on-site so video never leaves the premises and results survive a connectivity outage.

How it is built

Video is heavy. Moving it to the cloud for inference is often the most expensive design available. We push processing toward the camera and send results rather than frames wherever that is viable.

Typical stack

  • PyTorch
  • YOLO
  • OpenCV
  • ONNX Runtime
  • TensorRT
  • OCR engines
  • Python
  • Edge devices
  • MQTT
  • Docker
  1. L1

    Capture layer

    Camera selection, placement and lighting — where most accuracy problems are created or solved.

  2. L2

    Edge inference

    Quantised models on on-site hardware, so bandwidth and privacy stop being constraints.

  3. L3

    Event pipeline

    Only detections and clips of interest are transmitted and retained, not continuous footage.

  4. L4

    Retraining loop

    Misclassifications flagged by staff feed back into the next training round rather than being lost.

Where it connects

Capability in isolation changes nothing. These are the systems this normally has to reach in order to be useful.

  • Existing camera estate

    RTSP streams from the CCTV and IP cameras already installed, in most cases.

  • Operational systems

    Detections raised as ERP, MES or ticketing events rather than as another dashboard.

  • Alerting

    Notifications to the people who can act, with the supporting clip attached.

  • Reporting

    Aggregated counts and timings written to the warehouse for trend analysis.

What it looks like in operation

A defect detected on the line and raised as an actionable event, without a person watching a monitor.

  1. 01 Cameracapture
  2. 02 Edge inferenceon site
  3. 03 Classifydefect?
  4. 04 Confidence gatethreshold
  5. 05 Raise eventMES / ticket
  6. 06 Operator reviewfeedback

How we deliver it

The same six stages apply to every AI build we run. The evaluation set is created before development starts — without it there is no way to tell an improvement from a regression.

  1. 01

    Qualify

    Is a model the right instrument here? A deterministic rule is cheaper, faster and easier to audit when the problem allows one. We say so when it does.

  2. 02

    Prepare data

    Sources identified, access agreed, content parsed and indexed. Data quality sets the ceiling on everything after this point.

  3. 03

    Build the evaluation set

    Real examples with known-good outcomes, collected before any development. This is what makes later decisions measurable.

  4. 04

    Prototype and measure

    A working slice scored against the evaluation set — accuracy, latency and cost per request all measured rather than estimated.

  5. 05

    Integrate and guard

    Wired into the real system with permissions, rate limits, spend caps, fallbacks and human approval wherever the action is irreversible.

  6. 06

    Monitor

    Quality, cost and drift tracked after launch, with the evaluation set re-run whenever a prompt, model or data source changes.

The parts that decide whether it can go live

These are not add-ons quoted separately. They are the conditions under which a system like this is allowed near production data.

  1. 01

    Privacy by design

    On-device processing with faces and identifiers blurred or discarded where identity is not the purpose.

  2. 02

    Retention limits

    Only clips around a detected event are kept, on a defined schedule enforced by the system.

  3. 03

    Workforce transparency

    Where monitoring involves employees, we help you scope it to the operational purpose and communicate it honestly.

  4. 04

    Fail-safe behaviour

    Defined behaviour when a camera fails or a model is uncertain — never a silent gap in coverage.

Where this earns its place

  1. 01 Manufacturing

    Line inspection

    Catch defects at the point of production rather than at final inspection, when rework is far cheaper.

  2. 02 Construction

    Progress and safety

    Automated progress capture from site photography, plus PPE and exclusion-zone monitoring.

  3. 03 Logistics

    Load and label verification

    Confirm the right goods, quantities and labels before a vehicle departs.

  4. 04 Retail

    Shelf and queue monitoring

    Detect out-of-stock facings and queue build-up in time to act on either.

  5. 05 Healthcare

    Form and document capture

    Extract data from handwritten forms and printed records where digital capture is not yet in place.

  6. 06 Agriculture

    Crop and asset monitoring

    Assess condition and count from drone or fixed imagery across areas too large to inspect manually.

Computer Vision, answered plainly

Usually. Most IP and CCTV systems expose RTSP streams that we can consume directly. The limits are resolution, frame rate and position — a camera placed for general surveillance is often at the wrong angle for a specific detection task. We review your footage first and will tell you when moving a camera beats any model improvement.

It depends entirely on the task and the environment, which is why we will not quote a number before seeing real footage. Controlled conditions such as a production line can reach very high reliability; variable outdoor scenes with occlusion are harder. We agree precision and recall targets explicitly, because the cost of a false positive and a false negative are rarely the same.

No, and for most deployments it should not. Edge inference runs the model on-site and transmits only detections and short clips, which resolves bandwidth cost and privacy exposure at the same time. Cloud processing makes sense mainly for periodic batch analysis of already-stored imagery.

Typically a few hundred to a few thousand labelled examples per class, weighted toward difficult and edge cases rather than easy ones. We often start from a pre-trained model and fine-tune, which reduces the requirement substantially. Labelling is usually the largest single line in a vision project and we plan for it explicitly.

Footage nobody has time to review?

Send us a representative sample. We will assess feasibility honestly, including when the answer is to move a camera instead.

Free consultation

Free Consultation Available

Looking for a POS or ERP for your business?

Leave your name and number and tell us which product you are looking at. We will call or message you to understand what you need and prepare a quote.

Include the country code, for example +92 300 1234567

or

  • No obligation
  • English and Arabic
  • Six products