Indivd
•
•
Intro
An automotive retailer in Northern Europe achieved 98.9% absolute counting accuracy across all eight of its counting lines. The check covered 579 visitors, 19 opening hours and 4 camera positions.
An automotive retailer in Northern Europe put its complete counting setup into one quality assurance check. Across 579 visitors and 19 hours of opening time, all eight counting lines at four camera positions achieved 98.9% absolute accuracy against an independent count of the same hours.
Two trading days at an automotive retail location in Northern Europe. A customer can browse the floor, speak with a specialist, sit in a vehicle, take a test drive and return before making a decision.
One person may cross several counting lines during a single visit.
The retailer selected the hours and included every counting line in the check.
The store
A smaller visitor count can carry a high-value decision
The verification covered 579 visitors across 19 hours of opening time. At that volume, a small number of missed or additional crossings can noticeably change every ratio built on the visitor count.
The retailer had four camera positions, with both directions counted at each one. Those eight counting lines support measures such as visits per order, comparisons between trading periods and assessments of whether marketing activity brought more people into the location.
Automotive retail gives each visit particular weight. A customer may spend considerable time at the location without placing an order that day, while one completed sale can represent a significant result. Traffic alone does not explain performance. The relationship between visits and orders does.
That relationship requires a visitor count the retailer can trust.
The check
All eight counting lines were tested together
The retailer decided where, when and how much was tested. Across 19 hours of opening time, Indivd’s count was compared with an independent count of the same hours.
The check included 579 visitors and all eight counting lines across four camera positions. The complete selected setup was tested, rather than a sample of its counting lines.
The measure gives no credit for offsetting errors. Every missed entry, missed exit and overcount registers separately. Errors in opposite directions are never allowed to cancel one another.
The retailer can repeat the check during hours of its choosing and place the same test in the hands of another party.
DEFINITION
Absolute accuracy is 100% minus the absolute error rate.
Undercounts and overcounts are both errors. A missed entry, a missed exit, and a counted person who never crossed are each counted in full. Errors in opposite directions cannot cancel one another.
What the number carries
One verified result across the complete counting setup
Verified 18 January 2026: an automotive retailer in Northern Europe achieved 98.9 percent absolute people counting accuracy against an independent count of the same hours. The check covered 579 visitors, 19 hours of opening time and all eight counting lines across four camera positions.
The result covers the complete setup selected for verification. This matters because camera positions can differ in layout, traffic patterns and the way visitors move through them.
What the retailer gains is a verified denominator for visits per order, trading-period comparisons and evaluations of marketing performance.
A counting error does not remain at the entrance. Additional counts can make a campaign appear more effective than it was. Missed visitors can make a strong period look ordinary. Both can influence decisions involving far greater value than the visitor count itself.
The 98.9 percent result belongs to this deployment, at this location, during hours selected by the retailer. It is evidence of measured performance rather than a general product claim.
FAQ
What is people counting accuracy and how is it measured?
People counting accuracy is the difference between a system's count and an independent count of the same passages during the same hours. Under absolute accuracy, every missed entry, missed exit and overcount registers separately and errors in opposite directions never cancel.
How do you count visitors in a car showroom?
By measuring entries and exits in both directions at every entrance used, rather than at one main door. This location used eight counting lines across four camera positions, all tested together, reaching 98.9% absolute accuracy.
Can one visitor be counted more than once?
A counting line records crossings, so a visitor who moves between areas and returns has genuinely crossed more than once. In automotive retail a customer may browse the floor, speak with a specialist, sit in a vehicle, take a test drive and come back, which is why all lines are assessed together as one set.
Should every counting line be tested, or is a sample enough?
A sample tells you about the lines in the sample. Camera positions differ in layout and traffic pattern, so a result covering the complete set says more about a deployment than one covering only the easiest points.
How do automotive retailers measure visits per sale?
By dividing visits by orders across a trading period. It is the automotive equivalent of conversion, and it is only as stable as the visitor count beneath it, which is why the complete counting setup was verified rather than sampled.
Can a third party verify Indivd's counting accuracy?
Yes. The customer decides where, when, and how much is tested, can run the check without Indivd present, and can put the same test in anyone else's hands.