RETAIL
Employee Activity Monitoring
Employee Activity Monitoring. What it takes to run it.
Measure staff engagement and service levels in key zones.
// 01 · The question
“Is a key zone staffed when it needs to be?”
// 02 · Why it is hard
Staff and shoppers look alike, and the useful measure is engagement rather than headcount. The labelling standard has to define what serving looks like before anything can be trained.
// 03 · What the labels have to be
Bounding box + keypoints
Decided before the first frame
Presence in a zone is not service. Keypoints distinguish a member of staff facing a customer from one walking through, which is the difference between a coverage number that means something and one that does not.
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
Retail runs on shared NVR estates that get updated centrally. A codec or resolution change rolls out overnight, every zone drops together on the same date, and the model is fine. Check the recorder before retraining.
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