A station’s margin is made in the shop, not at the pump. We count how many drivers enter the shop on the cameras you already have, compare them with receipts and show you on which shift you are losing sales. No new hardware. We only recognize the employees you register; customers stay silhouettes, with no name and no profile.
North Station · 22:00 · 64 walk-ins · conversion 34%A single cashier after 22:00 · queue 5Coffee zone · +31% visits after moving next to the checkoutDay shift conversion 47% · night shift 34%Shift report · sent at every handoverChain · 12 stations measured the same way
What Vizor sees in a station
The pump sells on its own. The shop doesn’t.
Your back-office system tells you how many receipts were issued. Vizor tells you how many drivers came into the shop, how many left empty-handed and on which shift it happens. The difference is the margin you lose without knowing it.
0
Walk-ins vs. receipts, by shift
How many drivers come into the shop.
Real conversion for every shift and every station. The night shift has different traffic, different staff and, almost always, a different conversion rate.
queue 5 · one cashier · 22:40
Checkout queue, at night
How many wait, and for how long.
A single cashier at the evening peak means drivers who pay for fuel and leave without coffee. Above the threshold, an alert goes out.
Zones: coffee, impulse, fridges
Where they go and what they avoid.
Visit rate for the impulse shelf, the coffee zone and the fridges. A shelf that doesn’t sell may be a shelf nobody walks past.
What we don’t promise from day one: counting cars at the pumps and pump occupancy. The detector sees vehicles, but we haven’t yet measured its accuracy at a real station. We validate them in the pilot, at your station, and add them only if the numbers hold up.
Theft and shrinkage
We see when goods leave without passing the checkout.
In the station shop — alcohol, drinks, small expensive items — the same cameras watch for three theft patterns. When one occurs, an alert goes out with the exact time and the exact camera. At night, with only one person at the checkout, it counts double.
time · camera
Exit that bypasses the checkout
A person takes goods from a shelf and leaves the shop without passing the checkout. The alert includes the camera and the exact second.
02:14:07 · camera 2 · exit without checkout
expensive goods
Unusually long dwell
Someone lingers at the shelves with alcohol or expensive goods, outside the usual pattern for that hour. The cashier gets the signal before the person reaches the door.
23:40:15 · camera 1 · 5 min at alcohol
gesture, not product
Item hidden in a pocket or bag
The system watches the gesture, not the product: a hand moving from the shelf to a pocket, bag or coat. It is enabled only on the shelves you choose. If the person then leaves without passing the checkout, the alert gets top priority.
01:03:22 · camera 3 · reach toward a bag
Station dashboard
All stations. The same method, shift by shift.
The dashboard structure from the real installation. Switch stations and go through Dashboard, Alerts, Analytics and Reports. The numbers are illustrative; in an installation they come from the shop cameras and the station’s receipts.
app.vizor.md · fuel stations · dashboard
V
Vizor
On the phone
The same numbers, with the shift supervisor.
Stations run around the clock, and decisions are made on shift, not in meetings. The app is for whoever can change something within the next hour.
The alert lands on the lock screen, with the station, the camera and the minute.
Walk-ins, receipts and time at the checkout, for the current shift.
The shift report takes a minute to read, at handover.
The day’s numbers reach your phone, without customer names.
Reports for fuel stations
This is the report that arrives at shift handover.
Not presentation charts: the document the shift supervisor and the chain director receive, with the shift’s numbers and two masked frames. The same format as in the real installation; the numbers here are illustrative.
Shift report
North StationThursday, September 4 shift 14:00–22:00 · generated at 22:05 · 3 cameras
Shop walk-ins486+5% vs. last Thursday
Shop receipts192conversion 40%
Left without buying29460% · 118 of them after 21:00
Peak hours22:0064 walk-ins · conversion 34%
Time at checkout2:10max 4:50 at 22:40 · queue 5
Cashiers in the shop2 → 1the second one left at 21:00
By hour · walk-ins and receipts
Hour
Walk-ins
Receipts
Conversion
Max queue
14
46 / 22
48%
2
15
41 / 20
49%
2
16
50 / 24
48%
2
17
62 / 29
47%
3
18
67 / 31
46%
3
19
57 / 26
46%
2
20
52 / 22
42%
3
21
70 / 26
37%
5
22
64 / 22
34%
5
23
37 / 14
38%
2
Zones · of 100 drivers who come in, how many pass through each zone
Queue of 5 at checkoutNorth Station · cam 1 · 22:40. One cashier, wait 4:50.22:40
Queue back below threshold22:58 · wait 1:40. The previous alert closed itself.22:58
Shift report · 14:00–22:00Walk-ins 486 · receipts 192 (40%) · without a receipt 294 Peak 22:00, 64 walk-ins · max queue 5 at 22:40 Coffee: 12 of 100 · cashiers 2 → 1 at 21:00 Tomorrow: second person until 24:00.
Hours with the queue over threshold4734 of them after 21:00
Shop conversion ranking · same method at every station
Station
Conversion
Walk-ins
Δ wk
Queue > threshold
North
3,640
+2 pp
3 h
Center
3,980
+1 pp
4 h
East
3,210
0
4 h
Airport
4,120
+3 pp
5 h
West
3,050
−1 pp
5 h
South
2,890
0
6 h
M1 Highway
3,460
−2 pp
8 h
M3 Highway
3,380
−3 pp
8 h
Three recommendations
1M1 Highway and M3 Highway: the same traffic as North, 15 points lower conversion. Add a second person in the shop on the evening shift.
2Reposition the coffee at every station where the zone’s visit rate is below 20%: 7 of 12.
3North: conversion rose 2 points after the second shift was extended. The decision can be replicated at 5 stations.
Vizor · all locations measured the same way · aggregate numberspage 1 / 2
Analysis examples · fuel stations
Three scenarios, three decisions.
Our first real installations, in production, are in pharmacies in Moldova. For fuel stations we don’t yet have a client we can name publicly, so the scenarios below are modeled on the patterns measured there and on the retail analytics literature.
⚠ Modeled scenariosThese are not results reported by clients. We measure your numbers in the pilot.
Modeled scenarioStation with shop · night shift
A single cashier after 22:00. Drivers paid and left.
Problem
Coffee and impulse sales dropped sharply in the evening, even though fuel traffic stayed high.
What it showed
Between 22:00 and 24:00, 64 drivers an hour came in, with a single cashier. The queue went past 5 people, and conversion fell from 47% to 34%.
Decision
A second person in the shop from 21:00 to 24:00, instead of on the morning shift, when traffic is half as heavy. The same number of paid hours.
+8 ppnight-shift conversion, after four weeks
conversion by hour · before / after%
Modeled scenarioStation shop · 90 m²
The coffee was at the back of the shop.
Problem
The coffee machine, the most profitable product in the station, was selling below its potential, even though the price was competitive.
What it showed
Only 12 of 100 drivers who came in reached the coffee zone. The actual path went from the door straight to the checkout.
Decision
The machine was moved onto the path between the door and the checkout. Zero investment, one hour of work.
+31%visits to the coffee zone in two weeks
of 100 drivers, how many reach the zonebefore / after
Modeled scenarioChain · 12 stations
Almost equal traffic at the pumps. Shop results 40% apart.
Problem
The difference was blamed on the road and the area. The weak stations got campaigns, to no effect.
What it showed
Nearly identical shop walk-ins, conversion 28% vs. 45%. The difference was shift execution, not location.
Decision
A weekly chain-wide ranking and training at the weak stations, with the shift schedule rebuilt around real traffic.
+9 ppconversion at the weak stations, in six weeks
conversion ranking · 8 of 12 stations%
Our reference installation
The first location measured daily, with a parallel manual count and an automatic report every evening. The method is the same for a station shop; only the numbers differ.
The shop door and the checkout area are almost always covered. For zones, we add an ordinary camera if needed.
zero investment
02
Automated analysis
The video feed is analyzed continuously. Shift staff are told apart from drivers by behavior and position.
24/7
03
Numbers, not identities
Images are processed on the Vizor server; the report gets numbers. No customer identities and no license plates.
data minimization
04
Receipt matching
Hourly shop receipts are matched with walk-ins, which gives the real conversion per shift.
conversion
Privacy at the station
We don’t identify customers and we don’t read license plates.
The system follows silhouettes from frame to frame and turns them into numbers: how many came in, where they went, how long they waited. Images are processed on the Vizor server. Individual monitoring applies only to employees you explicitly register, with prior notice to them and the documented legal basis required by Law No. 195/2024.
Pilot for fuel station chains
Three stations. Three months. Numbers checked together.
One station on a national road, one in town and one on the outskirts, so the result says something about the chain. In the third week we count manually in parallel, on shifts you choose. You can stop the pilot at any time, with no penalty.
We don’t ask you for
New cameras
We work on the existing cameras in the shop. Where coverage falls short, we fill the gap.
We don’t ask you for
Station shutdown
Installation takes one day and doesn’t stop sales, either at the pump or in the shop.
We don’t ask you for
Long contract
Three months. Stop at any time. The comparative report on the three stations is yours to keep.
We don’t ask you for
Customer data
Only the video feed from the shop and, for conversion, the number of receipts per hour. Nothing about who filled up.
Calculator · what a conversion increase is worth
At a typical station, the conversion gap between the day and night shifts exceeds ten points. Here we calculate conservatively, with whatever figure you choose. A mathematical estimate, not a promise.
Extra sales per month291,600 MDL
extra receipts / month3,240
per year3,499,200 MDL
Calculation: walk-ins × days × conversion points × average receipt × stations.
Not from day one. Vizor measures the station shop: how many drivers come in, how many buy, how long they wait at the checkout, which zones they pass through. Vehicle counts and pump occupancy are validated in the pilot, at your station, and added only if the numbers hold up under a manual check.
Why does the shop matter more than the pump?
The margin on fuel is small and regulated. A station’s margin comes from coffee, snacks and impulse items, in other words from what happens in the shop. That is where it is lost or won, and that is where you have no numbers on real traffic today.
How is conversion per shift calculated?
Hourly shop receipts divided by the walk-ins counted in the same hours. We take the receipts from a daily export or through an integration. Shift staff are not included in the count.
Does it work at night?
Yes. The cameras in the shop have enough light, and the night shift is usually the most interesting one: heavy fuel traffic, a single cashier, low conversion in the shop.
Do you read license plates?
No. We don’t read license plates and we don’t identify customers. Camera images are processed on the Vizor server.
How long does installation take?
One day per station, without stopping sales, either at the pump or in the shop. The first shift report arrives that same evening.
Do you monitor shift staff?
You can. By default, cashiers appear only as the number of staffed positions, with no names. If you register employees in the system, they are recognized by face and can be reported individually — with prior notice to them and the documented legal basis required by Law No. 195/2024. Employee consent is not a valid basis, because employees are in a subordinate position: the basis is built on legitimate interest or on the occupational safety obligation, documented, with a data protection impact assessment and notice to every employee.
How do we start?
With a paid three-month pilot at three stations, which you can stop at any time, with no penalty. Before that, 30 minutes and a look at the cameras in one station.
Contact
Show us a station. We’ll tell you what we can measure.
We don’t ask for an hour-long meeting. You pick a station, we look at the shop cameras and reply within 24 hours, in writing, with what can be measured there.
What happens next
Three steps, no pressure.
1We reply within 24 hours, in writing, with what can be measured at your location.
2Thirty minutes on a single location: together we look at what your existing cameras cover.
3If it makes sense for you, we propose a pilot on three locations. You can stop it at any time, with no penalty.