Recognise
Recognition turns footage into a list of sightings you can search. Three separate things happen, each with its own limits: objects are detected, plate text is read and appearance is compared. Comparing faces is not offered in the current release.
- 1Detected · Car, followed on this camera
- 2Described · White car, plate read
- 3Seen again · A candidate at the next camera
- 4Kept · A still and a record to search
What is included
Detect people, vehicles and carried bags, read plates where they are legible, and find similar-looking sightings.
Detection
What is found in the picture.
People, vehicles and carried bags
People, cars, motorcycles, bicycles, buses, trucks, backpacks, handbags and suitcases, followed while they stay in view.
Limit: Detection quality depends on the scene, image quality, light, distance and camera angle.
Still frames for sightings
The clearest frame and the full scene are kept with the camera and the time, wherever a frame was captured.
Limit: VisionObject does not retain live video; the surrounding footage stays on your recorder.
Item left behind
A bag or a stopped vehicle that stays still beyond the time you set.
Limit: An event is recorded only when a rule fires, and each firing is an alert.
Plate reading
Text read from a plate, with a confidence value.
Number-plate reading
Optional moduleRead on vehicles large enough in the frame, on cars and two-wheelers. A plate that cannot be resolved is skipped, not guessed.
Limit: Not every visible plate is readable: small, distant, angled, dirty or poorly lit plates are skipped rather than guessed.
Vehicle route by plate
Optional moduleReadable sightings of one plate in time order, as numbered stops on a map. Only a one-stop route has been seen on live footage in our own testing.
Limit: Verified by automated tests; the only route recorded on live footage in our own testing had one stop.
Plate watchlist alerts
Optional moduleAn alert when a watched plate is read, showing whether the match was exact or near.
Limit: Verified by automated tests; not yet confirmed on a live feed in our own testing.
Appearance
What a sighting looks like, compared with others.
Colours and descriptive tags
Optional moduleFilter sightings by clothing or vehicle colour. Short descriptive tags are shown on each sighting.
Limit: Colours shift with lighting and camera settings.
Grouping across cameras
Optional moduleSightings that look alike are grouped as candidates for the same person or vehicle.
Limit: Groups rest on overall appearance, so similar clothing or similar vehicles can be grouped together.
Events it produces
What this capability watches for.
Each event 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.
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.
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.
Item left behind
A bag, case or stopped vehicle stays still beyond the time you set.
- When
- A backpack, handbag, suitcase or vehicle stays still past the limit.
- Limit
- Only the detected item types are covered, anywhere in the camera's view. A bag beside its seated owner can be reported.
Object present
A chosen kind of object is in a camera's view, such as a truck on a camera that covers a bay or a bicycle on one that covers a pedestrian area.
- When
- An object of the chosen type is present in the camera's view.
- Limit
- Limited to the detected object types, and to the camera's whole view: it cannot be limited to a drawn zone.
Outcome
Each sighting becomes a record with an object type, a still frame where one was captured and, where the modules are on, colours, tags and a plate.
Where it is used
See it working on footage like yours.
Tell us the workflow you care about. We will walk through it on demonstration footage, say what is available today, and plan a pilot on your own cameras.