Hands-on tutorial
Tutorials · AI
How to Set Up AI People Counting and Occupancy Analytics
Count visitors at entrances, measure occupancy and queues with AI cameras or edge analytics, and turn the data into staffing and layout decisions while respecting privacy.
Before you start
- Cameras with people counting, or an edge server running video analytics
- Entrance and area layouts
- A privacy assessment for the site
Step by step
Define the questions
Visitors per hour per entrance, current occupancy, dwell time in zones, or queue length at tills. Each needs a different camera position.
Position counting cameras overhead
For entrance counting, mount the camera looking straight down above the doorway, at the height the manufacturer recommends. Overhead views avoid counting errors from groups and do not capture faces.
Draw the counting line and direction
Place the line across the doorway, inside the camera view, and set which direction means in. Exclude staff doors.
Validate the count
Count manually for 15–30 minutes at a busy time and compare. Adjust height, line position and sensitivity until the error is acceptable.
Use zones for occupancy and dwell
For areas and queues, draw zones in angled cameras and set thresholds, for example an alert when more than five people queue.
Use the data
Send counts to reports or dashboards, compare by hour and day, and use them for staffing, opening hours and layout tests.
Pro tips
- Counting does not need identification: keep analytics anonymous and inform visitors with signs.
- Run analytics on the edge (camera or local server) so raw video does not leave the site.
- Check counts again after store layout changes.
FAQ
Frequently asked questions
How accurate is AI people counting?
Overhead counting at a well-lit entrance is typically very accurate; angled cameras and crowded scenes are less so. Always validate on site.
Is people counting legal under GDPR?
Anonymous counting is usually low risk, but you still need a legal basis, signage and a privacy assessment. Avoid facial recognition unless clearly lawful.
Keep learning
Related guides
AI smart events on IP cameras
Read more →Plan a network for AI video analytics
Read more →Run AI inference containers on NavEDGE
Read more →How to Use NavCloud AI Insights to Fix Problems Before Users Notice
NavCloud AI Insights turns alarms, inventory and telemetry from every site into a network health index and a short, prioritised list of findings with the action that fixes each one.
Read more →How to Set Up AI Smart Events on IP Cameras (Intrusion, Line Crossing, Human/Vehicle)
AI cameras classify people and vehicles on the camera itself, so you get far fewer false alarms from trees, rain and animals. Configure smart events and record only what matters.
Read more →How to Plan the Network for AI Cameras and Video Analytics
AI video means more streams, higher resolutions and analytics servers pulling video from many cameras. Size bandwidth, PoE and storage before you install.
Read more →Stuck on a step?
Ask Navijin technical support or an authorised partner for help with your configuration.