Restaurant Analytics: Turning CCTV into Real-Time Floor Intelligence.

A food-service operator was running on instinct — counting heads by eye, guessing peak hours, and reading table turnover from memory. Axlume turned the cameras already on the ceiling into a computer-vision system that counts customers, separates staff from guests, and tracks every table’s occupancy in real time.

Restaurant CCTV with a computer-vision overlay: customers and waiters tracked by ID, tables boxed as occupied or empty, and a live count of customers, waiters and empty tables.
Platform
Computer-Vision PipelineReal-Time AnalyticsOperations Dashboard
Services
Computer VisionDetection & TrackingML EngineeringVideo AnalyticsData VisualizationProduct Strategy
Scope
Customer CountingStaff vs. GuestTable OccupancyDwell & Empty TimeHeatmaps & TrafficReporting
01Overview

Our client runs a busy food-service floor and needed it to stop being a guessing game. Owners couldn’t see real peak hours, managers couldn’t read crowd conditions without walking the floor, and analysts had nothing but a recording — hours of CCTV that captured everything and told them nothing.

Axlume built an AI layer on the cameras already installed: a vision pipeline that counts customers, separates staff from guests, and tracks every table’s state in real time — turning passive surveillance into live operational intelligence for three roles: the owner watching revenue, the manager watching the floor, and the analyst watching the trend.

02The Problem

A camera that records everything and understands nothing.

Headcounts were done by eye and were wrong by lunchtime. Nobody could continuously watch every area of the floor, so peak rushes were spotted late and staffing during them was mostly guesswork.

There was no automated read on occupancy — which tables were full, how long they’d been full, how long they’d sat empty. Seating went under-used, traffic patterns went unmeasured, and the only “analytics” the CCTV produced was footage nobody had time to watch.

Every decision that mattered — when to add staff, how to lay out seating, when the rush really hits — rested on someone’s memory of a busy night.

The engine, live

Watch it read the room.

The vision layer running on a live feed — tracking each customer and waiter by ID, boxing every table as occupied or empty, and keeping a running count on screen. This footage is the proof the rest of the platform is built on.

Live detection & tracking
Real footage from the deployed system — customers (yellow) and waiters (blue) tracked by ID, tables flagged occupied (green) or empty (red) with elapsed time.
03How We Operated

We didn’t install new hardware. We made the existing cameras think.

The footage was already being recorded. The job was to extract intelligence from it — a lightweight, scalable pipeline that runs on a real restaurant feed, not a lab clip.

Discovery & Interviews

We spoke to the people who feel the gaps — owners wanting automated occupancy, managers wanting faster visibility into crowding, analysts wanting trends instead of tape. The recurring theme: CCTV that only records, never reports.

Strategy

We scoped a system around four outcomes: automate monitoring, extract business insight from the feed, cut manual workload, and put the numbers where a decision gets made — on a screen, in real time.

The Vision Pipeline

Frames are pulled from the stream; a detection model locates every person and classifies customer vs. staff; a tracker holds each identity across frames; and an occupancy layer reconciles people against tables to mark each one occupied or empty, with the clock running on both.

Engineering

Built as a modular pipeline — detection, tracking, occupancy and analytics as separate stages — so it stays light enough for a real venue and scales from one camera to many without a rewrite.

Delivery

Shipped as a working analytics layer: live counts and table states on the feed, plus the aggregated metrics that turn a night of service into a chart an owner can actually use.

04What We Built

Six parts that turn a feed into floor intelligence.

Component 01
Detection & Tracking

Every person on the floor located per frame and held as a stable identity across frames — the foundation everything else counts on.

Component 02
Customer & Staff Counting

People classified as customers or waiters, so the live count reflects actual demand — not staff walking the floor — and staffing can be read against it.

Component 03
Table-Occupancy Engine

Each table tracked as occupied or empty with the elapsed time on both — turnover, dwell time and idle seats become measurable instead of remembered.

Component 04
Heatmaps & Traffic Flow

Movement aggregated into traffic patterns and density over time — where guests cluster, which areas sit cold, how flow shifts through a service.

Component 05
Analytics Dashboards

The live read for managers and the aggregated read for owners — peak hours, occupancy curves and utilization, surfaced as visuals rather than raw footage.

Component 06
Automated Reporting

Historical performance and trend analysis generated without anyone scrubbing tape — the analyst’s view, produced on its own.

Detection in the wild

What the system actually sees.

Pulled straight from the live feed — not a staged demo. Crowded floor, real lighting, real angles, the model holding identities and table states throughout.

Live HUD counting customers, waiters and empty tables, with people boxed and labelled.
Live counts — customers, staff and empty tables, on the feed
Tables boxed green for occupied and red for empty, each with elapsed time.
Per-table state — occupied vs. empty, with elapsed time
Customers in yellow boxes and a waiter in a blue box, separated by the model.
Staff vs. guest — waiters separated from customers
05The Architecture

A modular pipeline, from camera to chart.

Four stages, decoupled so each can scale or be swapped on its own — the feed comes in, the AI makes sense of it, the analytics layer turns it into numbers, and the output layer puts those numbers in front of a person.

INPUT CCTV / camera feed Live or recorded streams Frame extraction AI PROCESSING Detection & tracking YOLO object detection Customer vs. staff Identity tracking Occupancy estimation ANALYTICS Turn pixels into metrics Customer & staff counts Table utilization & dwell Heatmaps & traffic OUTPUT Where decisions happen Live dashboards Visual reports Real-time monitoring
06The Outcome

From a wall of monitors to a number you can act on.

The floor went from observed to measured. Manual monitoring dropped, the rush stopped being a surprise, and the decisions that used to ride on memory — staffing, seating, timing — got a live read behind them.

What changed operationally:

Detection accuracy and deployment metrics are held under NDA. Contact us directly for a detailed brief.

07The Technical Reality

What this required.

Real computer vision in a real venue is the hard part — detection and tracking that hold up under crowding, fisheye lenses, mixed lighting and constant motion, not a clean benchmark clip. Holding a stable identity for a customer who keeps disappearing behind a counter is the whole game.

It was built hardware-light on purpose: it runs on the cameras the venue already has, so the analytics are a software deployment, not a refit. A modular pipeline — OpenCV and a YOLO-based detector at the core, with the tracking, occupancy and analytics stages decoupled — keeps it light enough for one venue and scalable to many.

The stack is deliberately pragmatic: Python, OpenCV, YOLO-based detection, deep-learning models, NumPy and Pandas for the analytics. The result behaves correctly on a live restaurant floor — not just in a notebook.

Next Case Study
Solidani salon management SaaS dashboard
Salon SaaS · Product Design

Solidani — Designing a Comprehensive
Salon Management SaaS

Product DesignSaaSDesign Systems
Ready to Scale

From Proof of Concept to Global Scale.

You’ve seen our standard of engineering. Now, let’s build yours. From high-impact websites to complex enterprise applications, we specialize in transforming ambitious ideas into elite-grade digital reality. Whatever the platform, we bring the precision your vision demands.