Traffic monitoring & enforcement

Every vehicle counted. Every speed measured. Every violation proven.

MIT Traffic turns roadside cameras into a traffic survey that never ends: virtual tripwires drawn on the frame count and classify every vehicle, calibrated cameras measure real speeds in km/h, and speeding, wrong-way and lane violations are captured with photo evidence and a human review queue. It also watches the road as it runs — stopped vehicles and queues raised as they happen, corridor journey times, and signal timings checked against your own measured demand. No loops cut into the carriageway, no radar, no survey crews.

car · 58 km/h ✓truck · 51 km/h ✓van · 78 in 60COUNTING LINEcalibratedSEGMENT — Airport Rd · limit 60LOS B · v/c 0.41SPEEDING 78 / 60 · sent for reviewtoday 12,481 vehicles · avg 58 km/hno loops · no radar
24/7
counting — not a two-week survey once every few years
±2%
speed accuracy against ground truth at urban limits
0
loops cut into the road, sensors buried or lanes closed
1 line
drawn on the frame is the entire installation
100%
of violations carry an evidence frame and a human decision
seconds
from a vehicle stopping to the incident being on screen
what you get

Everything the job needs, in one system

Virtual counting lines

Draw a tripwire anywhere on the camera frame and it counts from that moment. Endpoints are stored as fractions of the frame, so changing resolution or swapping the camera never moves your count line.

Classified, not just counted

Every crossing is typed — car, van, truck, bus, motorbike, bicycle — and directional, so you get composition and turning movements, not one anonymous number.

Calibrated speed in km/h

Mark a rectangle of known size on the road and the camera learns the ground plane. Speeds come from a least-squares fit over roughly a second of motion, not the gap between two frames.

Section speed as a fallback

Where a camera can't be calibrated, pair two lines with the distance between them and time vehicles over the section. Every pass records which method produced its speed.

Calibration you can verify

The system projects a metre grid back onto your camera image — if the grid lies flat on the road, the calibration is right. Impossible geometry is rejected when you save it, not discovered in the data months later.

Live detection view

Watch vehicles cross, typed and timed, in real time — commissioning a site is a few minutes of looking at the screen, not a week of waiting for data.

Flow, counts & level of service

Volumes by hour, day, direction and vehicle class, with flow rates, volume/capacity ratio and a Level-of-Service grade per segment.

Violations

Speeding, wrong-way, illegal stopping and restricted-lane use are detected automatically; red-light joins them wherever a signal-phase feed is available.

Human review inbox

Nothing is issued by a machine alone. Every violation lands in a queue with its evidence frame, its measured speed and its calibration record, to be approved or rejected — one at a time or in bulk.

Evidence, kept in proportion

Over-limit passes store a frame; ordinary passes don't. That's the difference between a few hundred images a day and a few hundred thousand.

Incidents as they happen

A vehicle stopped on the carriageway, a queue building, a car going the wrong way — raised within seconds, held open with a running duration, and cleared automatically when the road does.

Live road conditions

Every road graded free-flowing to congested from the speed traffic is actually doing. A road at capacity and a road that has broken down both carry high flow — only one of them is still moving.

Journey times & O-D

Match the same plate at two points and you have what a corridor really takes end to end, its reliability, and an origin–destination matrix showing where traffic goes next.

Signal timing advice

Enter the timings a junction runs and your measured demand says whether the green is shared out the way traffic arrives — or whether the cycle is simply longer than the demand needs.

Road network model

Model segments, their cameras, their speed limits and their zones, so counts and violations arrive already attached to a place on your network.

Export & reporting

Filter violations and passes and export them for enforcement, consultants or a council report — the raw data is yours, on your servers.

how it works

From camera to outcome in five steps

1Pointany road camera2Drawa line on the frame3Counttyped & directional4Calibratepixels become metres5Actevidence, incidents, advice
why teams switch

Tubes, loops & radar vs MIT Traffic

The traditional wayMIT Traffic
Getting countsBook a crew, lay pneumatic tubes, wait a fortnight, receive a PDFEvery vehicle, every day, already running — the survey never stops
InstallationCut inductive loops into the carriageway; close a lane to do itMount a camera, or reuse one you already have, and draw a line on the frame
Moving a count pointA new deployment, a new crew, a new invoiceDrag the line to somewhere else on the frame
ClassificationInferred from axle spacing, and only roughlyThe AI names the vehicle type on every single crossing
SpeedA radar box measuring one point on one laneAny calibrated camera, plus section speed over a known distance
EvidenceA number on a device, and an argument about itAn evidence frame, the measured speed and the calibration behind it
Who decidesWhatever the box recordedA person reviews every violation before it goes anywhere
How current your data isA survey from eighteen months agoA live dashboard, and the full history behind it
CoverageThe two or three points you could afford to surveyEvery camera on the network, at no extra hardware cost
Knowing a lane is blockedA phone call from whoever is stuck in itAn incident on screen seconds after the vehicle stops moving
Journey timesA consultant's floating-car study, a handful of runsEvery plated vehicle that drives the corridor, continuously
Signal timingsSet once at commissioning, reviewed when someone complainsChecked against the demand your own cameras measured this hour
the difference, in numbers

Measured against the old way

Time from decision to first counts
traditionalweeks — book a crew, lay tubes
MIT Trafficminutes — draw a line
Count points you can afford
traditionaltwo or three surveyed sites
MIT Trafficevery camera on the network
Speed error at 60 km/h
traditionalunverifiable without a radar audit
MIT Traffic2.3% against ground truth
Violations backed by reviewable evidence
traditionala reading, and a dispute
MIT Trafficframe + speed + calibration record
Time to know a lane is blocked
traditionalhowever long until somebody phones in
MIT Trafficseconds — it appears on the incident board
where it is today

Shipped, and what comes next

Phase 1

Counting & classification

Virtual counting lines, per-class and directional counts, live detection, and flow analytics with level-of-service grading.

Live today
Phase 2

Speed measurement

Ground-plane calibration with a verifiable metre grid, velocity-fit speeds in km/h, and paired-line section speed where calibration isn't possible.

Live today
Phase 3

Violations & review

Speeding, wrong-way, illegal stopping and restricted-lane detection, evidence frames, a human review inbox with bulk actions, and export.

Live today
Phase 4

Incident detection

Stopped vehicles, queues and wrong-way movements raised the moment they appear and cleared the moment they end, with a per-road threshold so a signal queue never reads as a breakdown.

Live today
Phase 5

Journey time & O-D

Corridor travel times and an origin–destination matrix built by matching the same plate at two points — where traffic actually goes, not where it was surveyed.

Live today
Phase 6

Signal advisory

Your own measured flows turned into signal-timing advice: whether the green is shared out the way demand arrives, and whether the cycle is longer than the demand needs.

Live today
Phase 7

Red-light enforcement

Crossing the stop line against a red. The detection is built; it needs a live signal-phase feed from the controller, which is a per-junction integration rather than a camera change.

On the roadmap

Every phase above marked shipped is running in production today, on the same cameras and the same calibration — nothing on this list required new hardware on the road once the first camera was pointed at it. Red-light is the one capability that depends on something outside the camera: a live phase feed from the signal controller.

competitive edge

The advantages competitors can't copy overnight

  1. 01

    Speed from motion, not from two frames

    Bounding boxes jitter by a pixel or two, and near the horizon one pixel can be a metre — so a two-frame speed is noise. MIT Traffic fits a velocity over roughly a second of tracked ground positions. Measured against ground truth: 1.7% error at 30 km/h, 2.3% at 60.

  2. 02

    Calibration you can see is right

    Every other camera-speed product asks you to trust a number. This one draws a metre grid back onto your road: if the squares lie flat, the geometry is right. Impossible quads are refused at save time rather than quietly producing plausible nonsense.

  3. 03

    Honest about how each speed was made

    Calibrated and section speeds have different error characteristics, so every pass records which one produced it. Nobody has to guess whether a number is defensible.

  4. 04

    Nothing is pre-aggregated

    Flow is computed from the raw crossings on demand, so correcting a line's position re-derives history instead of leaving a stale summary that disagrees with the detail.

  5. 05

    Enforcement with a human in the loop

    Automatic detection, manual decision. That's the design that survives a challenge — and the review queue is built in, not a spreadsheet someone maintains on the side.

  6. 06

    Alerts tuned to be worth reading

    A stopped-vehicle alarm that fires on every car at a red light is worse than none — operators stop looking. The threshold is set per road and has to clear a whole signal cycle, and a vehicle must have been moving before stopping counts, so parked cars never fill the log.

  7. 07

    Incidents end as well as start

    An incident is a condition, not an alarm: it opens, carries a running duration, and closes itself when the road clears. What you see is what is wrong now, not a list of everything that ever went wrong.

  8. 08

    Journey times that ignore the car that parked

    A vehicle seen an hour later didn't drive slowly — it stopped for lunch. Corridor times use a trimmed median, so a handful of stopped cars can't make a clear road look congested.

  9. 09

    No civil works, ever

    No lane closures, no loops in the asphalt, no radar to certify and re-certify. A camera and a drawn line replace the entire installation.

  10. 10

    One platform with security and parking

    The same cameras and the same server already running MIT Eyes can count traffic — and the same plate reading serves parking and investigations.

the platform play

Install once. Monetise four ways.

Your cameras+ one on-prem serverMIT EyesAI video intelligenceMIT ParkingANPR parking revenueMIT Attendanceworkforce attendanceMIT Trafficroad counts & enforcementyou are here

Competitors sell four systems: four installs, four vendors, four invoices. MIT sells one platform where every module reuses the cameras, the AI and the data of the others — so each solution you add costs a fraction and returns in full.

  • One enrolment, everywhere — a face enrolled for security also powers attendance.
  • One plate database — investigations and parking sessions share the same ANPR.
  • One set of rules — the same workflow builder emails on a hazard, a watchlist plate, a no-show or an over-speed.
  • Software, not hardware — the next module is a licence, not a construction project.

You can't manage a road you only measure every eighteen months.

See MIT Traffic running on your own cameras — a pilot takes a day, not a quarter.