VLM detection engine lets public safety operators create custom video detectors from plain-text prompts, with no dataset collection and no model training

MURRIETA, Calif., Sept. 11, 2026 /PRNewswire/ -- IREX, the ethical AI company from California, unveiled StreamVLM™, a Vision-Language Model (VLM) detection engine that turns a plain-language description into a working video analytics detector. AI-company claims it's a world's first VLM designed for cloud-based public safety platforms.

For the past decade, adding a new capability to a video analytics system has meant commissioning a new AI model: collecting a dataset, labeling it, training, validating, and deploying — a cycle measured in months and budgets. StreamVLM removes that cycle. An operator describes a condition in ordinary English — "detect a person lying on the ground," "alert when graffiti appears on a wall," "identify flooding in the underpass" — and the platform begins watching for it on the selected cameras.

"Public safety agencies have never been short on things they need to see. They have been short on time and money to build a model for each one," said Serge Smirnoff, IREX Head of PR. "StreamVLM changes who gets to decide what a camera network watches for. It is no longer a data science project. It is a sentence typed by the person who actually knows the neighborhood, the station, or the campus — and because it is IREX, every one of those sentences is logged, attributed, and reviewable."

A StreamVLM detector is a named set of prompts with its own settings, applied to selected camera channels. Each prompt is independent, with its own confidence threshold, alert cooldown, and event type. Selected frames from live camera feeds are evaluated continuously against the prompts by a VLM that understands images and language together, and matches generate real-time alerts within seconds.

A single camera channel supports multiple prompt-defined detectors at once. A station camera can simultaneously watch for a person on the tracks, platform overcrowding, an unattended bag, smoke, fresh graffiti, and flooding at platform level. Detectors can be added or adjusted at any time without taking the system offline.

StreamVLM sits alongside IREX's specialized analytics modules for faces, vehicles and traffic, weapons, perimeter, rail and transit, crowds, fire, and camera integrity — and extends them into territory no fixed module catalog covers: infrastructure damage, illegal dumping, snow and ice hazards, unattended objects, unauthorized vehicles, worksite safety violations, non-standard signage and vehicle markings, and conditions particular to a single city.

A detector that anyone can define in a sentence requires the same oversight as one that took a year to train, and StreamVLM is governed by the same mechanisms as the rest of the platform: prompts are recorded, events are auditable, access is role-based, investigations require a Case ID.

See the video here: https://youtu.be/xmlS0t6VUec

Media Contact:
Serge Smirnoff
422414@email4pr.com
+13012001194

View original content to download multimedia:https://www.prnewswire.com/news-releases/irex-unveils-the-first-vision-language-model-analytics-for-public-safety-302875967.html

SOURCE IREX Inc