The customer walks in
But you don’t know how many actually came in. The checkout only sees those who made it there.
1,240 walk-ins · 512 receipts
Vizor · video analytics for any location with customers
People counting on your existing CCTV cameras. See how many leave without buying.
Your till only sees the people who bought. Everyone who walked in and left without a receipt is missing from every report. Vizor shows you the rest, on the cameras you already have. We don’t just count:
Visitorshow many came in, hour by hour
Servedhow many reached the till or the counter
Lefthow many walked out without a receipt
Asked for, but missingwhat customers asked for that wasn’t on the shelf
Centru store · cam 1 · overhead viewlive simulation
walk-ins today0
bought0
no purchase0
in store0
customerboughtno purchasestaff, not counted
The problem we solve
The people who leave without buying never show up in any report.
1,240came in yesterdaycounted on existing cameras
−
512boughtreceipts from the cash register
=
728left without buyingdon’t appear in any sales report
Why?
Between 17:00 and 19:00 more people came in than at any other time of day. The checkout queue grew past 6 people, and conversion dropped by 11 points compared with the rest of the day. That window accounts for 312 of the 728 who left.
What to do?
Open a third checkout between 17:00 and 19:00, or move the second shift by an hour. No new hires, no investment. You’ll see the effect in the next day’s report.
An example from a supermarket with four checkouts. We measure your numbers during the pilot, with a parallel manual count.
The customer’s path
You know what sells. Do you know what happens before the sale?
Cash register data starts after the customer has decided to buy. Everything before that — walking in, browsing, giving up — doesn’t show up in any report. Scroll: the path draws itself.
The customer browses
But you don’t know which zones draw attention and which lose it. The aisle that doesn’t sell may be the aisle nobody walks down.
promo zone: 9 of 100 get thereThe customer leaves
But you don’t know why they didn’t buy. A queue, a product they couldn’t find, no one to answer a question. Each has a different fix.
728 left without buying · 59% of walk-insThe cash register starts counting after the customer has decided to buy. Vizor measures what happens before that.
Theft and shrinkage
We see when goods leave without passing the checkout.
The same cameras that count customers also watch for three theft patterns. When one occurs, an alert goes out — with the exact time and the exact camera. Checking it takes ten seconds instead of an hour of searching through recordings.
Exit that bypasses the checkouts
A person goes from an aisle straight to the exit without stopping at the checkouts. The alert includes the camera and the second.
18:42:07 · camera 3 · exit without checkout
Unusually long dwell
Someone lingers in the aisles with expensive goods, outside the usual pattern for that hour. An employee stepping into the area usually settles it.
16:15:40 · camera 2 · 6 min at cosmetics
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 instead of the basket. It is active only in the zones you choose — cosmetics, alcohol, small expensive items. If the person then leaves without passing the checkouts, the alert gets top priority.
11:03:22 · camera 5 · reach toward a bag
Who Vizor is for
One app. Seven industries, to start with.
A pharmacy chain director needs different numbers from a supermarket director, and a warehouse has no receipts, only loading docks and aisles. The system is the same: existing cameras, silhouettes, numbers by the hour. Each industry has its own page, with the metrics that matter there.
Real installation
Pharmacies
Walk-ins vs. served at the counter, queue, pharmacists per shift, peak hour.
View page → Analysis scenariosStores and supermarkets
Conversion vs. receipts, promo zones, checkout queues, chain ranking.
View page → Analysis scenariosFuel stations
Station shop by shift, night-time checkout queue, staff per shift.
View page → Analysis scenariosFinishing materials showrooms
Attention by zone, customers not greeted by sales consultants, visit duration.
View page → Analysis scenariosWarehouses
Aisle traffic, loading dock occupancy, congestion in shipping, unused zones.
View page → Analysis scenariosConstruction sites
People at the gate vs. the timesheet, zones without hard hats or vests, first and last movement.
View page → Analysis scenariosTraffic studies
Vehicles and pedestrians by interval, counted from video; the count can be redone at any time.
View page →Don’t see your industry?
If your business has physical locations and video cameras, Vizor can measure something useful. Tell us what you sell and how many locations you have.
Tell us about your business →The Vizor dashboard
All locations, across all industries. One picture.
The dashboard layout from the real installation. The demo below cycles through Dashboard, Alerts and Analytics on its own; click anywhere to take control. The numbers are illustrative.
app.vizor.md · dashboard
Comparethe performance of locations measured the same way.
Identifythe problem fast: location, hour, camera.
Trackthe trend over time, after every decision you make.
V
Vizor
On the phone
The same numbers, in the store manager’s pocket.
The mobile app is for whoever makes the call in the next minute: the shift supervisor, the store manager, the dispatch center. No tables, just the three things that matter right now.
- The alert lands on the lock screen, with the store, the camera and the exact minute.
- Today’s visitors, people who left without buying, and time at the checkout.
- The evening report takes a minute to read, in the app or in Telegram.
- The day’s numbers reach your phone, without customer names.
What changes
The same Monday-morning questions. Different answers.
We don’t change your process. We change what you know while you run it. On the left, how most companies answer today. On the right, the number and the decision that follows from it.
The questionWithout VizorWith Vizor
How many people came in yesterday?Without VizorAn estimate based on the number of receipts.With Vizor1,240 people counted by the entrance camera, hour by hour.
Why did conversion drop on Tuesday?Without VizorIt gets discussed in a meeting. Everyone has a different explanation, and none of them can be checked.With VizorBetween 17:00 and 19:00 the queue went over six people. Open a third checkout during that window.
Is the promotion zone working?Without VizorYou only see the sales figure. You don’t know whether nobody wants the product or nobody walks past it.With Vizor9 out of 100 customers make it there. Move the zone next to the main path and measure the effect.
How many people do we put on the evening shift?Without VizorSame as last year, plus the shift supervisor’s intuition.With VizorStaff and customers side by side, hour by hour. Usually you don’t lack people; you lack them at the right hour.
Why is the Sculeni location underperforming?Without Vizor“It’s the area.” The marketing budget goes there, with no measurable effect.With VizorSame traffic as the Centru store, with conversion 20 points lower. The difference is execution.
When do you find out there’s a problem?Without VizorIn next month’s report, when it’s too late to change anything.With VizorWithin ten seconds on the shift supervisor’s phone, with the location, camera and minute.
The numbers in the right-hand column come from a supermarket with four checkouts, used as an example. We measure yours during the pilot, with a parallel manual count.
Results and case studies
One real case, in production. And analysis examples, marked separately.
Real resultIn production at a client, with a manual count for verification
Real deployment · in productionpharmacy · Moldova
The first location measured daily, with a parallel manual count.
- Problem
- A pharmacy with one counter, existing cameras, and no numbers on how many people come in or how many leave unserved.
- What we measure
- Walk-ins and served customers by hour, pharmacists separated from customers, a daily evening report with masked images. A few hours a week counted manually, for calibration.
- What the client found
- The peak hour and the hour with the weakest service don’t match what the team believed. The numbers are checked together, not promised by the vendor.
Aug 2026in production; automatic report every evening
Read the case study on the pharmacies page →walk-ins by hour · a typical dayserved
⚠ Modeled scenariosThese are not results reported by clientsThe numbers below are built on the patterns measured in the pilot and on the retail analytics literature. They show how the data is used, not what anyone has achieved.
The promotion was good. Nobody walked past it.
9 out of 100 customers reached the promo zone at the far back of the store. Moved next to the main path: ×2.3 visits, +18% promo sales in two weeks.
The consultants stood on the left. The customers were on the right.
60% of customers’ time was spent in zone C; the sales consultants stood at the entrance. Repositioned using the attention map: −40% ungreeted customers in three weeks.
Two stores with identical traffic. Sales 35% apart.
Conversion was 28% vs. 44% at the same traffic. The difference was execution, not the area: training at the weaker store, +9 pp in six weeks, with no marketing budget.
Privacy and security
We analyze behavior, not people’s identities.
- Facial recognition only for registered employees
- Customers are never identified
- Images are processed on the Vizor server
- On your cameras, no new devices, privacy notice included
Pilot project
You don’t have to take our word for it. Test it at three locations.
Three locations, three months. Together we agree on what to measure, check the numbers against a parallel manual count and analyze the results; the decision to expand is yours. You can stop the pilot at any time, with no penalty.
We agree on what to measure
One large location, one small one and one neighborhood store, so the result says something about the chain.
We check the data together
In the third week we count manually in parallel, during hours you choose.
We analyze the results
The comparison report for the three locations is yours to keep, whatever you decide.
You decide if it’s worth it
No new hardware, no IT project, no long contract. The risk is three months and three locations.
Calculator · what a conversion increase is worth
In an ordinary store, the conversion gap between 14:00 and 18:00 is more than ten points. Here we calculate conservatively, using whatever increase you choose. An estimate, not a promise.
Extra sales per month194,400 MDL
extra receipts / month1,080
per year2,332,800 MDL
Calculation: visitors × days × conversion points × average basket × locations.
Check my location →Read also
Related pages.
Video analytics on existing cameras
What video analytics measures, which cameras it works on, what it costs and how accurate it is.
Read →People counters: which type to choose
Infrared beam, 3D sensor or your existing cameras: what each one measures and what it costs.
Read →Video analytics for showrooms
How many customers a consultant greets, how long they wait and which collections they skip.
Read →Vizor across Moldova
Installed in one day, then everything remotely: receipts from 1C, reports in Romanian and Russian.
Read →Frequently asked questions
The questions we’re asked most often.
What does customer counting on existing cameras mean?
Software reads the video from the surveillance cameras you already have and counts how many people come in, where they walk and how long they wait. No door sensors are installed and no cameras are replaced. The result is numbers by the hour: how many came in, how many bought, where a queue formed.
Does it work with existing cameras?
Yes. Vizor uses the cameras you already have, whatever the brand, as long as they see the entrance and the checkout area. We check coverage in our first conversation, on one location.
Do I need new hardware?
Usually not. Where coverage falls short, we add one or two ordinary cameras. The analysis runs on a small server, on your premises or in the cloud.
Does Vizor recognize people’s faces?
Yes, but only the faces of people you register in the system yourself — usually employees, who are informed in advance. Their paths are automatically labeled with their names: hours, zones, time on site. Customers and anyone else in the frame are not registered, so they remain counted silhouettes, with no identity and no profile. A facial template is biometric data: the privacy notice and the legal basis for employees are prepared together, as part of the pilot. Employee consent is not a valid legal basis, because employees are in a subordinate position: the basis is legitimate interest or the employer’s occupational safety obligation — documented, with a data protection impact assessment (DPIA) and notice to every employee.
What kinds of data can I see?
Walk-ins by hour, conversion vs. receipts, people who left without buying, checkout wait time, attention by zone, staff vs. customers, plus real-time alerts and the daily report in Telegram.
How long does implementation take?
One day per location, without closing. The first report arrives on the evening of the installation; calibration against a manual count is done in the first few weeks.
Can I test the system before rolling it out?
Yes. A pilot at three locations for three months, with the numbers checked together against a parallel manual count. You can stop at any time, with no penalty.
How is the data protected?
Camera images are processed on the Vizor server; customers are not identified, and identities exist only for the employees you register. The server can be yours. Dashboard access is role-based, and reports go only to the designated chats.
How much does Vizor cost?
It depends on how many locations you have and what can be measured on your existing cameras. We don’t sell standard packages: first we look at one location, write to you about what can be measured there, then send a quote. The usual first step is a pilot at three locations.
Does it work for multiple locations?
Yes, it’s built for chains. All locations are measured with the same method and appear in the same dashboard, so they’re directly comparable.
What is a customer counting system?
A customer counting system measures how many people enter a location and when. Traditionally this is done with a sensor mounted at the door; Vizor does it with the surveillance cameras you already have, with no new equipment. The result is the same — the number of visitors by the hour — but you also see where people walk, how long they wait at the checkout and how many leave without buying.
What is a people counting system?
A people counting system measures how many people pass a given point and when. The traditional option is a sensor or a dedicated camera mounted above the door. Vizor counts people on your existing surveillance cameras, using video analytics, with no new equipment — and, besides the count at the entrance, it gives you the paths across the sales floor, the checkout queue and staff separated from customers.
What’s the difference between a people counter and Vizor?
A people counter, or visitor counter, gives you a single number: how many people crossed the threshold. It costs €350–1,600 per door and has to be installed. Vizor uses your existing cameras and, besides the visitor count, gives you conversion vs. receipts, the zones people skip, the checkout queue and staff separated from customers. If you only need the number at the door, a counter is simpler; if you need to understand what happened inside, you need video analytics.
Do you need a sensor or a special camera to count people?
No. People counting can be done on ordinary surveillance cameras, as long as they see the entrance. We don’t install door sensors and we don’t replace cameras. We check coverage in our first conversation, on one location, and tell you honestly whether what you have is enough.
What is in-store traffic analysis?
Traffic analysis, or retail video analytics, measures how people move through a space: how many come in, which paths they take, which zones they stop in and how long they stay. It produces the numbers your cash register doesn’t have — foot traffic by hour, dead zones, crowding — which explain why a day’s sales look the way they do.
How is a store’s conversion rate calculated?
A store’s conversion rate is the number of receipts divided by the number of visitors over the same period. You already have the receipts in your cash register; visitors are the number that’s usually missing. We measure it on your existing cameras, hour by hour, and conversion calculates itself. Staff are not included in the count.
What is a store heat map?
A heat map shows, on the floor plan, where people stopped and where nobody went, over a day or a week. It’s used to see whether a promotion sits on a busy path or in a corner people walk around, and how many paid-for square meters bring in nothing.
Contact
Show us a location. We’ll tell you what we can measure.
We don’t ask for an hour-long meeting. Tell us what kind of location you have and how many there are; we’ll look at the camera coverage 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.