RETAIL
Traffic Counting & Conversion
Traffic Counting & Conversion. What it takes to run it.
Accurate footfall analytics filtered for staff and non-shoppers.
// 01 · The question
“How many shoppers came in, and how many bought?”
// 02 · Why it is hard
Staff, delivery drivers and people passing the door all have to be excluded, and the conversion figure is only as good as that filtering. Nothing about it is visible in a single frame.
// 03 · What the labels have to be
Bounding box + tracking
Decided before the first frame
A count is not a per-frame detection. The same person appears in hundreds of frames, so an identity has to persist across them or the number is a function of frame rate rather than of footfall.
This is the decision that is expensive to reverse. The geometry has to match what the answer contains, and finding out it does not means labelling the set a second time.
// 04 · How we run it
Three parts of one loop, on this job.
LexAnnotate
Shopper Tracking
Annotate in-store video for customer detection, employee identification, door events, and product placement. Distinguish between customers, staff (by uniform), and children within each camera's region of interest.
LexInsight
Conversion Analytics
Turn raw foot traffic data into conversion intelligence. Link visual detections to store zones, time slots, and operational events. Surface patterns that static dashboards miss.
LexAlert
Store Alerts
Monitor detection accuracy across store locations. Detect when camera repositioning, seasonal displays, or lighting changes degrade model performance. Route the failures back for retraining.
// 05 · What breaks it after launch
The counting line is drawn in image coordinates. A knocked or re-aimed entrance camera moves the line relative to the door, and the count changes on a day when footfall did not.
It is not the only one that can get this use case, it is the one that usually gets it first. All ten conditions.
// 06 · In retail
Store Intelligence
The Challenge
The models lacked high-quality labeled data, activity alerts came back false, and unmonitored registers left customers waiting at checkout.
Our Execution
Labeled customer and staff positions. Validated alerts and traffic counts for accurate footfall tracking.
The Result
Faster AI training with accurate labeling. Smarter alerts for open doors and empty registers.
4M+
Annotations & validations