Solutions

AI Traffic

One trainable AI for every road user. NOW Wireless has developed its own multipurpose intelligence for Smart Cities and traffic — it counts, classifies and tracks pedestrians, cyclists and vehicles on any IP camera, with full support for Urban Traffic Control (UTC) and Urban Traffic Management and Control (UTMC).

Long exposure of city traffic at night

The problem we solve

Cameras everywhere, insight almost nowhere

Most towns already have more cameras than operators can watch, and most detection still depends on loops cut into the road. One AI platform turns the cameras you already own into detectors, counters and incident alarms — covering detection, journeys, queues, turn analysis and ANPR, through to air quality, parking, Low Emission Zones and road user charging.

Up to 17Vehicle classes counted and classified
Any IP cameraExisting cameras become detectors
0Road works to replace an inductive loop
UTC & UTMCDirect interfaces to the control systems you run

Capabilities are delivered by one AI platform and are configured per camera. Feature availability depends on camera position, lighting and the control-system interfaces at each site.

One platform

One trainable AI for every road user

Our AI is multipurpose: the same engine counts, classifies and tracks pedestrians, cyclists and vehicles, and is trained for new tasks as they arise rather than bolted on as separate products. It runs on the street, in the control room or in the cloud, and feeds UTC and UTMC directly.

  • Detection, journeys, queues, turn analysis and ANPR from one engine
  • Extends to air quality, parking, Low Emission Zones and road user charging
  • Works on standard ONVIF‑conformant IP cameras — new or existing
Isometric illustration of a smart city with connected cameras, junctions and sensors

One AI, many uses — from the junction to the whole network.

Virtual loops

Detection without digging up the road

Traditional inductive loops are replaced by AI, sensors and a camera — no roadworks, no closures. Virtual loops count and classify pedestrians and up to 17 vehicle types, detect stop‑line presence, identify traffic hotspots and automatically trigger mitigation.

Ready for the forthcoming Advanced Real‑Time Traffic Management Systems (ARTMS) standard, where AI feeds richer detection into UTC and the on‑street controller equipment.

Signalised junction with cameras and sensors on the signal poles

Stop‑line presence and counts from the camera, not from a loop in the tarmac.

Traffic monitoring

Intelligent information for traffic managers

The AI watches every camera and alerts operators the moment something changes — slow traffic, stopped traffic and incident detection, with dynamic area‑of‑interest alerting so attention goes exactly where it is needed. It also interfaces with Connected and Autonomous Vehicles (CAV).

  • Areas of interest drawn and moved from the control room
  • Alerts to operators, UTC and the cloud
  • Every camera watched all the time, not just the ones on the wall
TRAFFIC MONITORING — AI ON AN EXISTING CAMERA any existing CCTV camera Dynamic area of interest — drawn and moved from the desk STOPPED LIVE ALERTS Stopped vehicle Slow traffic ahead Queue forming Incident cleared to operators, UTCand the cloud The AI watches every camera, all the time, and tells the operator where to look.The camera itself is unchanged.

A stopped vehicle inside the area of interest raises an alert; the camera itself is unchanged.

Start / end journey

Know where every journey starts and ends

Anonymous digital signatures tell us where pedestrians, cyclists and vehicles come from and where they are going. AI analysis of the collected data provides in‑depth insight into road use — device journeys across the whole day, and quick identification of non‑standard routing through streets that were not designed for it.

  • Bluetooth and Wi‑Fi signatures hashed — no one is identified
  • Origin, destination and route for the whole day
  • Rat‑runs and unexpected routing surfaced automatically
START TO END — WHERE JOURNEYS REALLY GO A B detectordetectordetectordetector rat-run through side street Expected route Route actually taken, start 07:42 — end 08:04 Anonymous digital signatures from Bluetooth and Wi‑Fi, hashed — no one is identified.

Expected route against the route actually taken — through a street that was never meant to carry it.

Queue detection

Spot the queue as it forms

Draw a zone on any camera and the AI watches it for queues — no movement, or slow movement, of a group of vehicles in the box. When a queue forms it triggers an alert to operators or a loop pulse straight to the traffic controller, with interfaces to UTC and the cloud.

  • Zones drawn, moved and resized remotely
  • Loop pulse to the controller, alert to the operator, event to UTC
  • An extra camera 50 to 100 m upstream extends detection
QUEUE DETECTION — A ZONE DRAWN ON ANY CAMERA Queue zone a group of vehicles stopped, or moving slowly QUEUE DETECTED → Alert to operators → Loop pulse to controller → Event to UTC and cloud → Length and time logged cleared when the queue moves Zones are drawn, moved and resized remotely.An extra camera 50 to 100 m upstream extends detection.

A queue zone on the approach: when traffic stops moving in it, the controller knows.

Turn analysis

Count every turn at every junction

Vehicles at junctions are counted and classified by the direction they leave. The AI tracks each vehicle through the junction in real time, classifying and counting as it goes, and provides an individual count for every direction you configure.

TURN ANALYSIS — COUNTED BY THE DIRECTION THEY LEAVE 1 3 2 4 COUNTS BY DIRECTION 1 → 3 ahead1,284 1 → 2 left312 1 → 4 right178 classified: car · van · HGV · buscycle · motorcycle · pedestrianevery direction, in real time

Every entry‑to‑exit movement counted and classified, live.

Desire lines

See how the road is really used

Every vehicle’s movement through the frame is tracked and drawn as a trace directly on the camera image — building up desire lines that show how road users actually move through a junction. It is a graphical, at‑a‑glance view of demand that no count alone can give, live in SenseView today.

Camera view of a junction with coloured desire-line traces drawn over the road

Desire lines drawn on the live camera image in SenseView.

ANPR

Number plates, classification and pollution rating

Automatic Number Plate Recognition (ANPR) adds journey times, turn analysis, start‑to‑end journeys and extended classification to any camera. Each plate can be checked against national vehicle records, returning the vehicle’s classification, fuel type, Euro status and pollution rating — with every plate hashed for privacy.

  • Up to 10 vehicles a second from a standard camera
  • Ghost and clone plate alerts where the plate does not match the vehicle — see Ghost Plates
  • Feeds Low Emission Zones, road user charging and journey‑time systems
ANPR — PLATE, CLASSIFICATION AND EMISSIONS BAND FROM ANY CAMERA AB12 CDE any existing camera · up to 10 vehicles a second Plate hashed for privacy VEHICLE DATA RETURNED ClassificationCar Fuel typePetrol Euro statusEuro 6 EmissionsCompliant Journey time12 min from national vehicle records,where authorised Adds journey times, turn analysis, start‑to‑end journeys and extended classification to any camera. Ghost and clone plate alerts where a plate does not match the vehicle.

Plate read, hashed and checked — classification and emissions band returned to the control room.

Bus & taxi

Priority for the vehicles that move the most people

The AI detects a bus and gives it a green wave, delays the light change while a bus is at the stop, and logs cars in bus lanes. Journey times come from ANPR or Bluetooth, temporary buses such as football coaches are recognised too, and everything interfaces to UTC and UTMC.

BUS AND TAXI — PRIORITY FOR THE VEHICLES THAT MOVE THE MOST PEOPLE BUS LANE BUS detected on approach car in bus lane — logged green wave granted RULES green wavehold greenat the stoplog bus laneviolations Journey times from ANPR or Bluetooth · coaches recognised as buses · dwell at the stop held Everything interfaces to UTC and UTMC.

Green wave for the bus, hold at the stop, and a record of the car that should not be in the lane.

Get in touch

Bring AI Traffic to your streets

Talk to our engineers about a trial on your existing cameras — from a single junction to a city‑wide deployment.

sales@nowwireless.com · 01883 621 100   |   Crown Commercial Service approved supplier · Manufactured in the United Kingdom