Staff presence and role monitoring with uniform detection
Nara counts how many staff are on duty at any moment, and tells managers, staff and customers apart by matching uniforms with its re-identification node, so no model training is needed. Operators compare staffing with demand and standards, and get an alert when it drops below the minimum.
[ 01 ]The problem
Staffing must match demand and standards, but managers lack a real-time view across stores.
- 01inputIn-store cameras
- 02processPeople detection; ReID matches each person against reference images of each uniform
- 03actionStaff counts per role over time, with an alert when below the minimum
How it works
Nara detects and tracks people in the store. Its ReID node compares each person with reference images of each uniform, such as manager and staff, and everyone else counts as a customer. Counts per role are stored over time and shown on dashboards, and an alert goes out when staffing drops below your minimum.
Works with Nara’s built-in models. You set up the zones, rules and outputs.
What you need
- In-store cameras
- Reference images of each uniform
- A PC or edge device running Nara in the store
Nara building blocks
- Camera nodes
- People detection
- Tracker with zone counts
- ReID with reference images per uniform
- Database table
- Dashboard
- Notifications
- AI model: People detection
- AI model: Person re-identification (ReID)
What it improves
- Staffing against demand
- Service standards
- Labour cost visibility across stores
[ 03 ]Where it runs
Proof from real deployments.
A global quick-service restaurant brand is piloting this to count managers, staff and customers in its restaurants.
FAQ
Questions, answered.
Do we need to train a model for our uniforms?
No. You add reference images of each uniform, and Nara’s ReID node matches people against them.
Does any video leave the site?
No. Nara processes video on your own hardware. Data is sent elsewhere only if you build a flow that sends it, for example an alert to your own MQTT broker.
Related
Related use cases
Queue monitoring
Long queues lose customers, and in factories work-in-progress builds up unseen until it stops the line.
cameranara seesPeople counting
Simple door counters double-count people who return or use several entrances.
cameranara seesVisitor demographics
Operators know how many people visit, but not who they are, which makes tenant, marketing and event planning guesswork.
Talk to us about staff presence monitoring.
Tell us about your site, cameras and machines, and we’ll show you how it runs on your own hardware, or download Nara and try it yourself.