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.

Intermediate9 min6 steps

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

  1. 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.

  2. 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.

  3. 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.

  4. 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.

  5. 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.

  6. 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.