Watchlist Recognition
Suspects and persons of interest your security team enrolled, matched as they pass a camera, with a Case ID on every privacy-sensitive search.
See Ethical Facial Recognition
Airport and Seaport Security under Continuous Demand
High throughput, and no quiet hour to catch up in. Thousands of passengers transit a terminal daily and the security demand never pauses, which makes this a scale and uptime problem before it is an analytics problem.
In Production
Dublin Airport
At Dublin Airport, IREX provides integrated airport security and business intelligence: suspect recognition against watchlists, unattended luggage detection in terminals and gate areas, weapon detection at access points, and crowd density monitoring to prevent dangerous congestion during peak travel periods.
The deployment is the demonstration that the platform operates in high-throughput environments where thousands of passengers transit daily and security demand does not pause. That is where the availability guarantees stop being marketing: every component hot-swappable, triple-replicated storage, automatic failover, and 24/7 monitoring of every platform component under Premier Support.
IREX also brings AI-based airport security to Peru, and seaports and ports of entry use the same modules with borders and customs workflows layered on top.
Coverage
Terminal, Apron, and Perimeter
Unattended Items
A bag left in a terminal, a gate area or an interchange, raised while the concourse around it is still moving.
See Abandoned Object DetectionWeapon Detection at Access Points
A firearm shown at a controlled entry, and the gunshot, scream or breaking glass that goes with it, routed to security in seconds.
See Weapon & Gunshot DetectionCrowd Density
Queue and concourse monitoring with real-time alerts, plus precise counting for capacity planning.
See Crowd ManagementPerimeter and Restricted Zones
Intrusion detection and restricted-zone monitoring across airside boundaries and port estates.
See Perimeter Intrusion DetectionVehicle and Plate Control
Plate and vehicle-attribute recognition at gates, car parks and freight entrances.
See License Plate RecognitionOn Camera
One Traveler, Two Cameras — and the Water Side
Two of these three frames are the same traveler at two points of one terminal, fifteen minutes apart: that is what a tracking result looks like when it is returned rather than assembled by hand. The third is the half of a port estate that has no fence.
Male, 34, Orange jacket · Dublin · 10:21:48
Follow, Rather Than Search Again
Once a subject is picked, the platform carries him camera to camera on appearance rather than re-running a face match at every step — which is what keeps working when he turns away from the lens.
Male, 34, Orange jacket · Dublin · 10:29:12
Eight Minutes Later, Landside
Same person, different camera, different concourse. A terminal is one estate, so the result is a route with times on it instead of a stack of unconnected sightings.
Object Tracking
Boat approaching · Alexandria · 06:12:47
The Water Side of a Port
A port estate does not stop at the fence. Vessel detection on the approach gives a harbor operation the same warning a landside perimeter already gets.
FAQ
Can it run at terminal throughput?
Yes, and Dublin Airport is the production reference. A single instance is proven at 100,000+ cameras with real-time analytics and 30-day instant search, and the architecture scales linearly across cameras, users, retention and active modules.
What happens if part of the system fails during a peak?
Every component is hot-swappable and can be replaced under load without operator-visible downtime, storage is triple-replicated with automatic failover, and there is no single point of failure. Under Premier Support the IREX network operations team monitors every component 24/7.
Do you handle business intelligence as well as security?
Yes. Continuous event export to Apache Superset gives customizable dashboards, which at an airport typically means passenger-flow heatmaps, dwell and queue statistics, and capacity planning alongside the security picture.
Do we have to replace our cameras?
No. Reusing the existing fleet is the standard deployment model: any camera that supports ONVIF or streams RTSP with H.264 or H.265 on a static IP can be connected, and each module then sets its own resolution and placement requirements, which a site survey confirms. Note that connection is not plug-and-play: a qualified network engineer configures each camera and router.
Who owns the data?
You do. Customers retain 100% ownership and control of their data, and IREX neither owns nor accesses customer video, events, logs, watchlists, or floor plans. On-premises deployment is the data-residency mechanism.
How do we start?
With a pilot: one site, three to five use cases, six to twelve weeks, and two or three measurable success criteria agreed in writing before it begins. Accuracy is benchmarked on your own cameras, and the measured numbers go into the contract.
Pick Your Worst Hour
Airport analytics should be judged at peak, not at 3am. We will scope a pilot around your busiest period.