Is the data anonymous?
Yes. Heatmaps track people as shapes moving through zones. No faces are stored, no one is identified, and nothing leaves the site except aggregate heatmaps, paths, and dwell figures.
Zone heatmaps and dwell time from the cameras already on the ceiling — anonymous, on-premise.
Flagship — Abdali Mall
--:--
Today
1,284
In store
37
Avg dwell
1m 12s
Entrance
1,284 · dwell 14s
New arrivals
842 · dwell 1m 36s
Checkout
611 · dwell 2m 22s
Back wall
203 · dwell 38s
edge-store-01 · healthy
by hour
Heatmaps show how people use a physical space: where they go, where they slow down, how long they stay in each zone, and which displays or areas they pass without stopping.
Store, mall, and venue teams see which zones work and which are ignored, without surveys or clickers, from the cameras already installed.
Tracking runs on-premise and is anonymous by design: no faces are stored and no individual is identified. Only heatmaps, paths, and dwell figures leave the site.Dashboards compare zones, days, and locations side by side, and exports plug into the reporting you already do for layout and staffing.
See where people slow down, which aisles or areas they skip, and how traffic spreads across the floor through the day.
Measure how long people stay in front of a display, a counter, or any area you draw on the camera view.
Put zones, days, and locations side by side to see what a layout change or a promotion actually did.
Powered by IFA
Runs as a module on the IFA edge box beside your cameras.
The IFA dashboard
Every IFA module reports into the same web dashboard. A new module shows up with its charts, events, and automations the day it is deployed — nothing is coded per module.
Plant overview — today
Events per hour
Events by severity
184 events · 2 modules · 4 cameras
Streams
Automation runs
Every camera as a health card: online, degraded, or offline, with frame rate, latency, and uptime, and a live view from the edge box when it is streaming. Refreshes on its own.
Pick a metric, group by line, zone, severity, or product, and bucket by hour, day, or week. Line, bar, area, stacked, and pie — all built from the events a module emits, never hand-coded.
Every event, filterable by module, type, and severity, with the frame that triggered it. Email and WhatsApp notifications go out through automations, with a per-run record of what was sent and what was suppressed.
A drag-and-connect flow builder: a trigger (a module event, a camera going offline, a schedule), logic (filter, window, cooldown, time gate), then actions — send an email, send a WhatsApp message, capture the frame, generate a report.
A report action turns a session or a shift into a readable document — totals, shares, per-product detail — attached to the notification email and kept in the dashboard's report list.
Heatmap questions
Yes. Heatmaps track people as shapes moving through zones. No faces are stored, no one is identified, and nothing leaves the site except aggregate heatmaps, paths, and dwell figures.
It depends on camera placement and coverage, so each camera view is checked during the pilot before numbers go live. Areas a camera cannot see are marked as uncovered rather than filled in.
Existing overhead or angled CCTV with an RTSP/ONVIF stream usually works. Where an entrance has no usable view, a standard IP camera is added. Processing runs on a small on-premise unit in the store or a server for a mall.
Last updated: