People Counting & Visitor Analytics
Count visitors with high accuracy and calculate conversion from real data.
Revenue alone does not explain a store’s performance. “We sold little” and “few people came in” are entirely different problems with different remedies.
When door counting is done properly, conversion becomes measurable; staffing, window changes and campaign effects can be compared on the same scale. Staff and delivery traffic are filtered out and double counting prevented; data is processed anonymously with no facial recognition.
How it works
Entry and exit separated
Counting uses direction, so someone waiting at the door is not counted twice.
Staff filter
Staff and courier traffic are removed to give net visitors.
Match with POS
Receipt counts are matched with visitor counts to compute conversion.
Conversion is a store’s most honest indicator
Revenue growth sometimes comes from more visitors, sometimes from better selling. Conversion is the only metric that separates the two. The hourly breakdown shows that in most stores peak traffic coincides with the lowest conversion — a loss that staff scheduling can fix directly.
| 10:00–12:00 · conversion 31% | 31% |
| 12:00–14:00 · conversion 24% | 24% |
| 14:00–17:00 · conversion 19% | 19% |
| 17:00–20:00 · conversion 16% | 16% |
| 20:00–22:00 · conversion 28% | 28% |
Evening hours are the busiest but the lowest-converting slot: shifting till and customer-service staff into these hours is the first step.
| W1 | 19 |
| W2 | 20 |
| W3 | 21 |
| W4 | 21 |
| W5 | 22 |
| W6 | 23 |
| W7 | 23 |
| W8 | 23 |
The gain was achieved without any campaign change — purely through staffing and queue management.
Use cases
Store entrance
Net visitor and conversion measurement.
Floor and corridor
Traffic distribution by area.
Store benchmarking
Fair comparison across stores.
Capacity tracking
Live occupancy and threshold alerts.
Technical requirements
| Camera | Overhead camera at the door; 2.6–4 m height ideal |
| Accuracy | 95–97% band after calibration |
| Data | Anonymous; no facial recognition or biometric records |
| Integration | POS, ERP, CRM, BI tools, REST API |
| Reporting | Hourly/daily traffic, conversion, store benchmarking |
Frequently asked questions
How does People Counting & Visitor Analytics work?
Revenue alone does not explain a store’s performance. “We sold little” and “few people came in” are entirely different problems with different remedies.
Are our existing cameras suitable for this solution?
Required camera specification: Overhead camera at the door; 2.6–4 m height ideal. Before installation we assess your camera inventory free of charge and report which points are suitable and, if needed, which camera should be added.
How accurate is it in the field?
Measured accuracy: 96.2%. Evening hours are the busiest but the lowest-converting slot: shifting till and customer-service staff into these hours is the first step. Thresholds are calibrated on your own site during the pilot.
Which systems does it integrate with?
POS, ERP, CRM, BI tools, REST API. Events are published over REST API and MQTT, so it connects to your existing MES, ERP, VMS and alarm infrastructure.
Is it compliant with KVKK, Türkiye's data-protection law?
Footage is processed on an edge server inside your facility; raw video is not sent to the cloud. Facial recognition is not used; analytics outputs are anonymous and event clips are deleted automatically when the defined retention period ends.