Moonlight Analytica Request demo
Physical-space intelligence

Cameras become a live operating model of your floor.

Janus turns ordinary cameras into zones, dwell data, queue depth, and role-aware people tracking — without surveillance creep. Generic CV tells you what it sees. Janus learns what your location means.

+53%
Promo dwell lift
4.4s
Avg wait time
94%
Model confidence
42ms
Inference latency
janus.moonlightanalytica.com / convenience-store
Janus dashboard: convenience store with live overlay cards — Staff 4, Promo dwell +53%, People in line 2, Avg wait 4.4s
🕳️

What happens on your floor is invisible to analytics.

You can see clicks, carts, and conversions — but the physical floor is a black box. Do shoppers actually pause at the promo display? Are staff crowding the areas customers need? Which zones turn into bottlenecks before a complaint surfaces? That gap kills margin in silence.

Janus closes this gap
01
Cameras streamYour existing CCTV or IP cameras; no new hardware required.
02
Role recognition separates who is whoCustomers, staff, security, and vendors are classified at 94% confidence, so every metric is staff-excluded by default.
03
Zones, dwell, and queues become live dataEvery named zone streams occupancy, dwell time, and queue depth at 42ms latency.
04
Operators act on the intelligence layerStaffing, promo placement, and layout decisions driven by what the floor actually shows — not gut feel.

The numbers Janus actually produced.

Promo dwell lift
+53%
Convenience store promo aisle. Shoppers (staff-excluded) dwelled 53% longer at instrumented displays.
Table dwell
+22%
Restaurant deployment. Guest-only table dwell increase — staff movement excluded from the signal.
Congestion reduction
+19%
Transit / subway deployment. Crowd flow improvement after Janus flagged bottleneck zones.
Tracked simultaneously
17
People tracked in the convenience deployment. Staff (4) automatically separated from customers.

From restaurants to transit systems.

The same Janus stack — role recognition, zone intelligence, dwell tracking — adapts to any physical environment where people move and operators need to act.

Janus restaurant dashboard showing table dwell analytics
Restaurant
+22%
Table dwell — guest only, staff auto-excluded
Janus transit dashboard showing crowd flow data
Transit
+19%
Crowd flow · Janus flagged congestion zones before queues formed
Inside the dashboard · live capability views

Generic CV tells you what it sees. Janus learns what your location means.

Every location has its own personnel mix, camera geometry, and problem regions. Janus ships six modules that train the system on your site — not a generic retail floor — so every metric you see is calibrated to your reality.
👤

Role Recognition

Classifies every detected person as customer, employee, security, or vendor. All downstream metrics are staff-excluded by default — you see only what your customers do.

👔

Uniform Classifier

Learns your specific uniform colors and patterns to reliably separate staff from guests even when they move through the same zones, across lighting conditions and camera angles.

📐

Camera Blind-Spot Tuning

Maps every camera's coverage geometry and confidence envelope. Signals from low-coverage angles are down-weighted automatically, so no dead zone inflates your numbers.

⚠️

Problem-Region Detection

Identifies zones that repeatedly generate queue buildup, low dwell, or staffing gaps. Surfaces the pattern before it becomes a complaint or a lost sale.

🔄

Track Recovery

Re-identifies individuals after occlusion or camera handoff, maintaining continuous track IDs across your full floor — not just within a single camera's view.

📊

Confidence & Coverage Scoring

Every metric ships with a coverage score and confidence band. You know exactly how reliable each number is — not just the headline figure, but the uncertainty around it.

Vertical intelligence matrix
VerticalCustomer metricsStaff separation signalsKey use case
RetailShopper traffic (employee-excluded)Promo dwell by real shoppersStaffed vs unstaffed promo liftTrue promo ROI; endcap optimization
RestaurantTable service responseGuest table dwellStaff vs guest movement ratioHost-stand queue; server coverage gaps
HotelGuest lobby dwellCheck-in queue depthStaff vs guest lobby presenceFront-desk staffing; amenity uptake
CasinoPatron table dwellFloor circulation patternsDealer/staff vs patron separationTable game utilization; floor optimization
Security / OMCPublic zone occupancyRestricted-zone intrusionAuthorized vs publicGuard patrol coverageAccess control verification; patrol gaps

See your floor become data.

We instrument your existing cameras and deliver a live Janus intelligence layer — no new hardware, no long procurement cycles. Most deployments go live in under two weeks.

No surveillance data leaves your premises · 94% model confidence · 42ms inference