We see it. We count it.
Computer vision that turns the cameras you already have into automatic counters. The model is trained on your own images and the processing happens on site: the number leaves, the video does not.
Demonstration scene. The number of detected objects is computed in real time from the objects visible in frame.
Try it with an image of your own.
Drop in a photo: your car park, your roof, your street. The detector downloads and runs inside your browser, not on our server.
generic model · COCO · Apache-2.0 This demo runs a generic, openly licensed model — not one trained for your scene. It detects cars, people and boats; it does not detect roof tiles or overflowing bins. That gap is precisely what we sell.
- Objects detected
- —
- Inference time
- —
Your image never left your browser.
That is how our product works too: the processing happens where the camera is. What travels is the number.
Want this accuracy on your real scene? We train on your images. →
One engine, four shop windows.
Each vertical is a different configuration of the same platform: same capture, same inference at the edge, same dashboard. What changes is the class being counted and the colour it is drawn in.
Car parks
How many cars are there now, and how many there were every hour last month.
Your security camera is already recording the car park. It just needs someone to read what it sees — and that someone need not be a person.
See car park occupancy → Comptam TeulesRoofs
The exact number of tiles on a roof, from a twenty-minute flight.
No scaffolding, nobody climbing onto the roof, and no margin of error in the materials estimate.
See drone roof inventory → Comptam FondeigAnchorages
How many boats, exactly where, and how long they stay.
The sea is a perfect plane: four reference points are enough to turn pixels into real coordinates.
See anchored vessel counting → Guaitam ResidusWaste
An alert when bulky waste appears or the bin overflows. Within minutes.
Not next week when a neighbour complains: twenty minutes later, with a photo and the exact location.
See illegal dumping detection →The loop that makes it more accurate every quarter.
This is not a model you install and forget. It is a six-step cycle that repeats for as long as the subscription runs, and every turn improves it on your specific scene.
- 01
Capture
Real frames of your scene, shot with the final camera and spread across days: sun, overcast, night, rain, full and empty. Variety before volume.
- 02
Curate
Every frame with detections in the uncertain confidence band is kept for review, along with the false positives you report. It is free fuel.
- 03
Annotate
The current model pre-annotates and a human corrects. Annotating this way costs 60 to 80 % less than starting from scratch each time.
- 04
Train
Fine-tuning on cloud GPU. A bespoke model costs a few euros of compute and under an hour.
- 05
Validate
Against a frozen test set that never enters training. No model ships without beating the previous one on that same set.
- 06
Deploy
The new model goes down to the node. Then round again: the scene keeps changing, and the model with it.
That is why the subscription is not rent in disguise: you pay for a model that gets more accurate every quarter, not for a server staying on.
The video stays where the camera is.
We process on the device itself and send only the number. Less data to protect, less bandwidth, less paperwork.
Frame → inference → discard. The node stores no video.
| GDPR principle | How the product meets it |
|---|---|
| Minimisation (art. 5) | Only a number or a state leaves the device. The image does not travel. |
| Privacy by design (art. 25) | The personal datum never comes into existence outside the node. |
| Storage limitation | Frames are processed and discarded; there is no continuous recording. |
| Proportionality | The camera does not identify people: it counts objects. |
A generic model has seen millions of cars. None of them was yours.
We train on images of your scene: your angle, your optics, your shadows at six in the evening. That is why it gets right what others get wrong.
It has seen millions of internet photos. None from your pole, with your optics and your video compression.
It has seen your scene in sun and rain, full and empty. Two hundred images of the real site beat nine million generic ones.
-
The domain gap
A public model has seen cars, but it has not seen your car park from your pole with your palm tree’s shadow at 18:40 in July. That distance is where detections get lost.
-
Variety before volume
150 to 300 images spread properly across sun, overcast, night, rain, full and empty beat 2,000 all taken at the same hour.
-
Your taxonomy, not a public dataset’s
We define the class you need to count, not the one the catalogue ships with. Your “car” may include the van that public datasets call a truck.
-
Non-negotiable validation
50 to 80 images per client are frozen and never enter training. No model ships without being compared against them.
The number lands where you already look.
Grafana, MQTT, your own API, or a Telegram message to the crew. We are not asking you to open yet another tab.
This is what leaves the node
{
"site": "hotel-x-parking",
"ts": "2026-08-03T18:40:12Z",
"class": "car",
"count": 37,
"capacity": 48,
"state": "normal",
"conf_mean": 0.91,
"model": "hotel-x-parking@v2.1"
}A count fits in two bytes. That is why a node can publish over LoRaWAN from a pole with no coverage and no SIM.
Let’s start with one camera.
Six weeks, one point, a real number on a real dashboard. If it works, we scale.
- Occupancy dashboard and history
- Alerts by Telegram or email
- Node maintenance
- 1 retraining per year
- Everything in Bàsic
- REST API and integrations
- 2 retrainings per year
- Business-hours SLA
- Multi-site
- Quarterly reports
- Tender support
- Support for the data protection officer
Getting started
| Feasibility study | 600 – 1,200 € | Site visit, scene analysis, written report with expected accuracy. Deducted from the project. |
| Pilot · one camera, 6 weeks | 1,500 – 2,500 € | Initial dataset, bespoke model, node installed and dashboard. |
| Additional bespoke model | 1,500 – 3,500 € | Depending on the number of classes and difficulty. |
| Edge node, installed | 900 – 1,800 € / point | Hardware, configuration, calibration and commissioning. |
| Drone campaign · roofs | 450 – 900 € / building | Flight, processing and report. |
How we work
- The pilot is never free. A free pilot has no committed counterpart. It is deducted from the rollout if it converts.
- The subscription is justified by retraining, not by hosting. We sell increasing accuracy, not a server staying on.
- Hardware is invoiced separately with an honest margin. We do not bury it inside the fee.
Indicative prices. The final figure is set in the feasibility study, after seeing the scene.
Let’s start with one camera.
Four answers and we will tell you whether your scene is viable. No sales call in between.