For city operations centres and the agencies that share them. Each agency keeps its own cameras, rules and watchlists. Cameras are shared one by one with named agencies, and aggregate traffic and coverage figures stay available without opening up anyone's searches.
- 1Northern approach · 10:41 · first seen
- 2Market square · 10:43 · seen again
- 3Depot gate · 10:44 · seen at the gate
- 4Southern approach · 10:46 · last seen
The problems we start from
Who it is for
- City operations centre lead
- Traffic management
- Municipal information technology
- Participating agencies
An incident crosses agency boundaries
Each agency sees its own cameras. Nobody sees the whole path.
Sharing everything is not acceptable
An agency will share a camera for a purpose, not its watchlists or its searches.
The health of the estate is unknown
Cameras from many suppliers, and no single view of which are working.
One workflow, step by step
An incident that moves between agencies
Scenario. A vehicle of interest moves from a traffic corridor into a municipal market area.
Each agency is its own organisation
It has its own cameras, rules, alerts and plate watchlist on the shared deployment.
Share specific cameras
A platform administrator shares a named camera with a named agency. The change is recorded.
Scope each person
Every member has a role and, where needed, a list of the cameras they may see.
Trace across what you may see
A plate search covers only the cameras visible to the person searching. Stops are shown in time order; lines between them are inferred.
Keep alerts with their owner
A shared camera raises each agency's own alerts from its own rules. One agency never sees another's.
Read the aggregate figures
Counts by vehicle type and hour on a corridor, and camera health by area. A viewer can read these and browse sightings, stills, events and alerts on the cameras in their scope, but cannot run plate, scene or route searches or group sightings. There is no figures-only role.
Measures
Four measures, each with a definition.
Defined so that two people would compute the same number. None is a result: the values come from your pilot.
- Incident stages
- Alerts raised, marked Acknowledged and marked False positive, with the median time to mark, per agency.
- Measured from: Alert statistics in Insights.
- Corridor events
- Count events, and wrong-way and stopped-vehicle events, per corridor per day.
- Measured from: Events filtered by area.
- Source freshness
- The time since each camera last delivered a frame.
- Measured from: Camera health.
- System health
- The share of cameras online, and the delay between capture and analysis on each camera.
- Measured from: Camera health and the per-camera status on the live wall.
Events of interest
Events for corridors, junctions and public spaces.
Each says what it needs and where it stops. The rules you set on a camera raise these events, and the alerts that go with them.
Wrong-way movement
A vehicle, or a person on foot, crosses a line against the permitted direction. Each rule names the object type it applies to.
- When
- A line crossed in the direction the rule forbids.
- Limit
- A vehicle reversing briefly, or a person stepping back, crosses the line the wrong way.
Vehicle stopped where it should not
A vehicle stays in a no-stopping zone, a fire lane or an emergency bay beyond the time you set.
- When
- A vehicle's time inside the zone passes the limit.
- Limit
- A vehicle held in traffic inside the zone is reported like a parked one.
Vehicle counts by type
Cars, buses, trucks, motorcycles and bicycles counted for each camera, by quarter-hour, hour or day.
- When
- Each followed vehicle is counted once in every period in which it is seen.
- Limit
- A vehicle that leaves the view and returns is counted again, and one seen across two periods is counted in each. Vehicle types outside the detected set are counted as the nearest type or not at all. Counts cover the last 30 days.
Crowd gathering
More people are in a camera's view at once than the number you set.
- When
- The count of people in the camera's view reaches the threshold.
- Limit
- A count of people the camera can see, not a calibrated density and not a count inside a drawn zone. People hidden behind others are not counted.
Occupancy threshold
The number of people or vehicles in a camera's view reaches the capacity you set.
- When
- The count of the chosen object type reaches the threshold.
- Limit
- It counts what one camera can see, so a space covered by several cameras needs a rule on each.
After-hours presence
A person or vehicle is in an area during the hours it should be empty.
- When
- Zone entry inside a scheduled window.
- Limit
- The schedule follows the clock, so authorised late work raises it unless that camera is excepted.
Plate on watchlist
A plate that is read matches an entry on your organisation's watchlist.
- When
- A plate read matches a watched plate exactly, with commonly confused characters treated as the same, or within one character.
- Limit
- A plate that cannot be read cannot be matched. A near match must be compared by a person before anyone acts.
Camera offline
A feed stops arriving. The platform keeps trying to reconnect and shows the camera as offline until the picture returns.
- When
- The feed is still missing after repeated reconnection attempts.
- Limit
- A camera that streams a frozen picture can look healthy. The alert repeats while the feed stays down.
Use cases
What a city operations centre uses it for.
What the current release does for this kind of site.
Share cameras between agencies
Each camera shared with named organisations, and withdrawn at any time
Role and camera scope
Each person sees only the cameras their role and scope allow
Corridor traffic counts
Vehicles by type and hour, filtered by area
Wrong-way and stopped vehicles
Direction and dwell rules on lanes and junctions
Crowd thresholds in public spaces
An alert when the people in view pass a number
Estate health
Each camera online, degraded or offline, by area
Vehicle investigation
One plate's readable sightings across the cameras you may see
What it needs
- An agreement between agencies on which cameras are shared, with whom and for what purpose
- A platform administrator who assigns camera ownership and sharing
- Camera locations entered for the map
- Area labels on cameras, so figures can be filtered by corridor, ward or department
Pilot objective
With two agencies and one shared corridor, show that each sees only what it has been granted, that a vehicle can be traced across the shared cameras, and that a viewer can read the aggregate figures and browse sightings in their scope without being able to run a plate, scene or route search.
Read the pilot guideBoundaries
- Sharing is per camera and per organisation. An agency never sees another agency's rules, watchlists, alerts or searches.
- Withdrawing a share stops access at once. It also hides that camera's past alerts from the agency that lost it.
- Retention periods are set once for a deployment, not per agency.
- There is no combined view across organisations: a platform administrator works organisation by organisation, and separate deployments are not joined.
- Each deployment runs on one machine at one location. A site keeps working through a network interruption only if the platform runs at that site.
- Aggregate figures do not show an individual's movements, but the sightings behind them are kept, and every role can browse them on the cameras in its scope. Plate, scene and route searches are limited by role and written to the audit log; filtering sightings by colour is open to every role and is not recorded as a search.
Capabilities used
The same platform. Different rules.
Each site gets its own cameras, modules and rules. Nothing is custom-built; everything is configured.
Object and vehicle recognition
Detect people, vehicles and carried bags, read plates where they are legible, and find similar-looking sightings.
Behavioural analytics
Turn movement into events with rules built from four things: geometry, time, counts and, where enabled, an AI scene reading.
Advanced video analytics
Analytics that go beyond a single camera or a single frame, each with what it measures and how far it has been evaluated.
Plan a scoped city-operations pilot.
Choose two agencies and one shared corridor. We will show what each can see, a vehicle traced across the shared cameras, and the aggregate figures.