Assess Incidents with More Context
Review relevant camera views and alerts to understand what is happening and support informed response decisions.
See Real-Time Crime Centers
Help officers assess incidents, investigators find relevant footage and command teams coordinate response. IREX brings video search, real-time alerts and secure communications together using compatible cameras your agency already operates.
In Production
IREX supports public-safety operations across North America, Latin America, Europe, the Middle East and Central Asia, connecting video intelligence and operational workflows within the requirements of each deployment. What follows describes the kind of work the platform does in each region, not a list of accounts.
In North America, police departments run traffic and incident detection, weapon detection in public spaces, loitering and registered-offender monitoring near sensitive locations and watchlist matching integrated with local law-enforcement databases. In Latin America, national and municipal forces use IREX as the backbone of public-safety operations, unifying large camera estates into centralized command infrastructure, with facial recognition, traffic analytics including two-wheeler detection and weapon detection and with agencies collaborating in real time through shared dashboards and secure messaging.
In Europe, the platform runs on transport, aviation and stadium estates: railway and platform safety, crowd and unattended-item detection, watchlist recognition at terminals and banned-entry lists at national sporting venues. In the Middle East, retail estates run watchlist face recognition for loss prevention. In Central Asia, national smart-city and traffic-enforcement programs run the module catalog as the central intelligence layer for public safety.
The same platform is designed to run at three scales: a single agency connecting its own cameras and tools, a municipality sharing situational awareness across authorized teams and locations and a national program with access, hosting and operating responsibilities defined across participating agencies. That last pattern is described in full on the Government as a Service page. These are supported deployment scopes, not a count of installations.
Outcomes
Review relevant camera views and alerts to understand what is happening and support informed response decisions.
See Real-Time Crime Centers →Search available video by time, location and supported person or vehicle attributes. Review potential matches and follow relevant sightings across connected cameras.
See Ask IREX & Video Search →Use Sover secure communications to share incident information with authorized personnel and support coordination between the command center and the field.
See Sover Communications →How It Works
Four steps, in the order an agency actually works. AI results are investigative leads that require human review, never a finding on their own and never an automated dispatch or a confirmed identity.
Begin with an alert, a reported vehicle, or a person description.
Examine relevant footage, location and time information.
Share relevant information with authorized personnel.
Maintain the supported case references and audit records for review.
On Camera
A description, a vehicle and a child. These are illustrative examples on demonstration footage, not actual cases and each label shows the shape of a query rather than a measured detection.
Sex, approximate age and appearance attributes are filters over the archive, so a witness statement becomes a query. This is appearance search rather than identity recognition: it returns people who match a description, not a name and a hit is a lead for an officer to confirm. The Case ID and lawful basis are recorded before the search runs.
Plate plus make, model, color and body type, checked against stolen, uninsured and unregistered records where that integration is in place and authorized. From one sighting the platform can reconstruct the route across connected cameras, in both directions in time.
See License Plate Recognition →
A missing-person description run across connected cameras at once. The match here is the shirt, the height and the time rather than the face, which is what an appearance search looks like when no enrolled image exists.
See Missing Persons →Use Cases
Each of these runs on the same connected estate. Sensitive identification capabilities carry their own controls, linked from every card.
Bring relevant video and supported threat alerts into the response workflow. Acoustic detection depends on suitable audio sources and enabled modules.
Read More →Narrow video review using time, location and supported search attributes, then follow a subject camera to camera in both directions in time.
Read More →Review potential sightings using available descriptions and authorized search tools, with the lawful basis recorded before the search runs.
Read More →Search plates and supported vehicle attributes to identify relevant sightings. Database checks require a supported interface and agency authorization.
Read More →Give authorized teams a shared view of relevant incidents and camera locations across the estate.
Read More →Share operational information through Sover secure communications, from the phone an officer already carries.
Read More →Governance
Deployment
Review camera compatibility, hosting requirements, information security, integration scope and total cost with your operational, IT and procurement teams. Define responsibilities and evaluation criteria before deployment.
IREX can work with compatible cameras. Camera streams, network access, image quality and the requirements of each selected analytic are reviewed during technical assessment.
Integration scope depends on the systems involved, the available interfaces and agency authorization. Endpoints for wanted-persons, stolen-vehicle, vehicle-registration and civil-registry systems are agreed during the design phase, with the customer providing timely access. Confirm the supported workflow and the implementation responsibilities during design.
Hosting depends on the selected deployment model. Document the location, retention settings, access permissions and support responsibilities before deployment. On-premises deployment is the data-residency mechanism.
AI results support human review. Officers and analysts evaluate potential matches and alerts alongside other information and agency procedures. A match is a lead to confirm, never a finding on its own.
Agree on use cases and measurable criteria, then evaluate them on representative footage and infrastructure. Include missed detections, false alerts, review time and operating conditions where relevant. Accuracy is benchmarked on your own cameras and the measured numbers go into the contract.
Review the documented IREX security posture and the proposed deployment with your agency security team and request the relevant control mapping. IREX aligns with the FBI CJIS Security Policy; that is an alignment and compliance-support position rather than a third-party certification and the applicable policy version and control mapping should be confirmed for your deployment. Confirm the responsibilities of IREX, the hosting provider and the agency.
Request an agency demo to discuss your use cases, infrastructure, procurement process and evaluation requirements. A pilot is the normal next step: one site, three to five use cases, six to twelve weeks and two or three measurable success criteria agreed in writing before it begins.
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.
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.
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.
Keep Reading
Tell us your operational priorities and the systems you use today and we will help define the right demonstration and evaluation scope.