The Tool Desk
Outbyte PC Repair FREERepair Windows errors before they cause bigger problemsFix Now →Outbyte Driver Updater FREEFix the driver behind crashes, sound loss and screen glitchesFind Drivers →iTechGuides is reader-supported. When you buy through links on our site, we may earn an affiliate commission. As an Amazon Associate I earn from qualifying purchases. Learn more
Metropolitan Nashville Public Schools’ Omnilert camera-based system did not detect the gun drawn during the January 22, 2025 shooting at Antioch High School, and it did not alert police. MNPS said the shooter was too far from the cameras for an accurate reading; Omnilert’s CEO said the firearm was not visible. The available reporting confirms the missed alert but does not establish which factor—or combination of factors—caused it.
What happened at Antioch High School
The January 22, 2025 shooting
The shooting occurred in Antioch High’s cafeteria in Nashville. WSMV reported that 17-year-old Solomon Henderson killed 16-year-old Josselin Corea Escalante, injured another student and then died by suicide. That is two deaths including the shooter and one student injured.
What the security system did not do
WSMV reported that the Omnilert system was installed and functioning, but it did not identify the weapon when it was drawn. Because no detection occurred, the system did not send an alarm to police. The failure was in the system’s detection-and-alert chain, not in a later decision by police to ignore an alarm.
How Omnilert’s camera detection was supposed to work
Omnilert CEO Dave Fraser told CNN that the software continuously analyzes school-camera video for visible guns. When it identifies one, the platform sends detection information, an image, a short video and the camera or building location to a human verifier. Fraser said emergency response begins in under 20 seconds in most cases after detection. That timing is a company description, not an independently audited performance guarantee.
#1 Best Overall
- AI Motion Detection 2.0 – Driving AI to the next level, human&vehicle detection and flexible detection area are more accurate than before. For quicker locating in crucial moments, human&vehicle smart searching in recordings offers you great help.
- Tried-and-True Safe Guard – This one-stop security solution can work with TVI, AHD, CVI, CVBS & IP cameras, the kit includes 1080P cams. The 8CH 3K lite DVR can hook up with 1080P@30fps or 3K/5MP@20fps cams. Therefore, you can also DIY it with other cameras in your home.
- Reliable 24/7 Continuous Recording – With a pre-installed 1TB HDD(Support up to 10TB HDD), providing 24/7 surveillance recording for you. Upgraded H.265+ saves more storage space and uses less bandwidth, recording videos longer and smoother viewing.
- Smart Dual-Light Effectively Guard Your Home – This newly upgraded security system offers you a crisp full color night vision, IR mode and color night vision switch flexibly. Once detect intruders, immediate pushes pop up on your phone, securing your peace of mind day&night.
- Color Night Vision & IP67 Weatherproof – Built-in IR lights and white lights, these cameras can see up to 100ft in B&W night vision, full-color night vision up to 66ft. Rated IP67, these wired cameras can brave all weather, and stand from cold to hot.
The workflow has an important consequence: the firearm must be visible with enough size, clarity and context for the camera and model to recognize it. Camera coverage, mounting position, viewing angle, lighting, distance and obstructions therefore affect whether the first step happens at all.
Why did the AI gun-detection system fail?
MNPS’s explanation: distance and image quality
MNPS spokesperson Sean Braisted told CNN that, based on the shooter’s position relative to the cameras, the weapon did not activate the system. In a statement recounted by Ars Technica, Braisted said the imagery “wasn’t close enough to get an accurate read and to activate that alarm.”
Omnilert’s explanation: the gun was not visible
Fraser gave CNN a separate explanation: the firearm was not visible to the cameras. Braisted also described the district’s account this way: “Based on the shooter’s position and location relative to our cameras, the system was not activated by his weapon.”
Rank #2
- 【AI Motion Detection 2.0】Driving AI to the next level, human&vehicle detection and flexible detection area are more accurate than before. For quicker locating in crucial moments, human&vehicle smart searching in recordings offers you great help.
- 【Tried-and-True Safe Guard】This one-stop security solution can work with TVI, AHD, CVI, CVBS & IP cameras, the kit includes 1080P cams. The 8CH 3K lite DVR can hook up with 1080P@30fps or 3K/5MP@20fps cams. Therefore, you can also DIY it with other cameras in your home.
- 【Reliable 24/7 Continuous Recording】With a pre-installed 1TB HDD(Support up to 10TB HDD), providing 24/7 surveillance recording for you. Upgraded H.265+ saves more storage space and uses less bandwidth, recording videos longer and smoother viewing.
- 【Smart Dual-Light Effectively Guard Your Home】This newly upgraded security system offers you a crisp full color night vision, IR mode and color night vision switch flexibly. Once detect intruders, immediate pushes pop up on your phone, securing your peace of mind day&night.
- 【Color Night Vision & IP67 Weatherproof】Built-in IR lights and white lights, these cameras can see up to 100ft in B&W night vision, full-color night vision up to 66ft. Rated IP67, these wired cameras can brave all weather, and stand from cold to hot.
What is confirmed—and what is not
- Confirmed in the incident reporting: the gun was not detected and the system did not alert police.
- Attributed explanations: MNPS points to distance and an image that was not clear enough; Omnilert points to the weapon not being visible.
- Unresolved: the available reporting does not determine whether distance, visibility, camera angle, lighting or more than one of these factors was decisive.
How much did MNPS pay for Omnilert?
MNPS approved a contract worth more than $1 million in 2023 for an AI detection layer over the district’s camera network and related security infrastructure. CNN reported that Omnilert was deployed across district schools in February 2024.
The figure is a rounded, districtwide contract amount. The reporting does not establish how much, if anything, was allocated specifically to Antioch High School, so it should not be described as a $1 million price for one campus.
What the 2026 lawsuit alleges
In June 2026, Ars Technica reported that an injured teenage survivor sued Omnilert and reseller System Integrations in Davidson County court. The complaint alleges that the companies knew or should have known about operational limitations involving camera placement, proximity, camera angle, lighting and weapon visibility.
Rank #3
- INCREDIBLE 12MP UHD IMAGE -- Mind-blowing 12MP PoE home security camera system becomes affordable for your home and business security. Subtle details are recorded to ensure your peace of mind.
- FULL COLOR NIGHT VISION -- The Spotlight of the 12MP outdoor surveillance cameras enables a full color night vision. You can schedule it to work at a time period and switch to IR LED mode other time flexibly. The spotlight can also be Motion-activated to deter intruders working with the siren.
- SMART HUMAN/VEHICLE/PET DETECTION -- Reolink latest smart cameras can now identify people, vehicles, and pets according to their shapes and minimize unwanted alerts.
- TWO-WAY TALK -- The 12MP camera of this home security system has a speaker built-in for two-way communication with your family as well as threat deterrence. Simply press a button on Reolink App or Client to talk.
- 16 POE PORTS, EXPANDABLE TO 24 CHANNELS -- The NVR with hardware version N6MB01 offers 24 channels for Reolink PoE, plug-in Wi-Fi cameras, and specific battery-powered Wi-Fi cameras (Argus PT Ultra, Argus Eco Ultra & Argus 3 Ultra for now, with more supported models in the future) with the latest firmware. Ensure battery cameras and Reolink App are updated. Supports a maximum of 16 PoE/plug-in Wi-Fi cameras.
Those are allegations, not findings that the defendants were negligent or legally liable. The reporting did not identify a judgment establishing fault. Ars said Omnilert’s cofounder declined to answer its questions about the case and the reseller did not respond to its request for comment.
Can an AI camera detect a hidden or out-of-view gun?
Not reliably if the weapon never appears clearly in a camera’s view. Omnilert’s described process is based on recognizing visible guns in video, so a firearm that is occluded, outside the frame, too distant, presented at a difficult angle or obscured by poor lighting may not produce a usable detection. That is a limitation of coverage and visibility, not proof that every AI gun-detection product behaves identically.
Camera placement also creates blind spots inside a building. A system can be operating continuously and still miss an event if the relevant scene is not captured at sufficient resolution. The Antioch accounts illustrate why “installed and functioning” does not mean “guaranteed to identify every weapon.”
Rank #4
- Total Property Coverage with Revolutionary 2-In-1 Design: Secure every corner of your property with zero blind spots. In this 4-camera bundle, every single device does the work of two. The innovative Triple-Lens system combines an upper 4K bullet lens (130° wide view) with a lower 2K PTZ lens that locks on, tracks, and zooms. Get both the complete scene and crucial close-ups at the same time. It’s the perfect all-in-one security solution for large estates, sheds, rental.
- AI Tracking from Close-Ups to Cross-Zones: Each camera independently utilizes AI to lock on, auto-frame multiple subjects, and zoom in for crisp details up to 164 ft away. Linked by the HomeBase S380, the 4-camera bundle takes it further with true Cross-Camera Tracking. As someone walks through your property, the cameras hand off the target seamlessly, stitching the activity across different zones into one continuous, timestamped video.
- Forever Solar Power & Effortless Setup: Skip the hardwiring and professional installers! Equipped with an ultra-large 5.5W solar panel and SolarPlus 2.0 tech, just 1 hour of direct sunlight daily keeps your camera running year-round. Thanks to this 100% wire-free, smart detachable design, you can easily mount and set up the camera anywhere in just minutes.
- No Subscription & Guaranteed Privacy with HomeBase S380: This bundle securely stores all your footage locally on the HomeBase S380’s 16GB built-in drive (expandable with any 2.5" drive). Beyond massive storage, the hub unifies all 4 cameras into one easy-to-use app. Featuring local BionicMind AI, it learns to recognize familiar faces, drastically reducing false alerts so you’re only bothered by real threats. Starting with 4 cameras, this highly scalable system can easily support up to 16 devices total.
- Precise Detection, Powerful Deterrence: Radar and PIR sensors deliver precise motion alerts with fewer false alarms. When a threat is detected within your set zone or schedule, red and blue warning lights and a 105 dB siren activate to deter intruders.
Do AI gun-detection systems prevent school shootings?
CNN’s February 2025 report quoted school-safety and privacy experts who said there was no data proving that AI gun-detection software prevents school shootings at that time. They described the technology as too new for a settled evidence base. This is a statement about the evidence available in that report, not a claim that no later study could change the picture.
Omnilert’s CEO described the product as one layer rather than a singular solution. ACLU senior policy counsel Chad Marlow told CNN, “There’s no intervention that is guaranteed to prevent a school shooting. If so, we’d all be using it.” After the Antioch shooting, MNPS also began installing entrance-screening scanners at the school, creating a different security layer rather than replacing the camera system with a proven winner.
Free tools Windows power users keep installed
One-click scans. No signup required.
Camera AI versus entrance screening: what should be compared?
Available reporting does not support ranking video AI and entry scanners by effectiveness. They address different points in the security process and should be evaluated on the same practical criteria.
| Evaluation point | Camera-based AI | Entrance screening scanners |
|---|---|---|
| Where detection occurs | Throughout areas covered by interior or exterior cameras | At a controlled entry point |
| What must be detected | A firearm must be visible in the video view and clear enough for analysis | An item must pass through the screening point and meet the scanner’s detection conditions |
| Coverage risks | Camera position, distance, angle, lighting, resolution and obstructions | Unscreened entrances, bypasses, queue design and items not presented to the scanner |
| Human involvement | Omnilert’s described workflow sends an image and video to a human for verification | Staff typically operate the checkpoint and respond to scanner indications; the exact workflow depends on the school |
| After an alarm | Requires verification, notification and an emergency response | Requires staff intervention and a decision about the person or item at the checkpoint |
| Known performance in this case | Did not detect the Antioch weapon or alert police | MNPS began installing scanners after the shooting; the reviewed reporting does not establish their performance in this incident |
| Independent evidence and cost | The reviewed reporting gives no independently established prevention rate, false-alert rate or per-school cost | The reviewed reporting gives no comparative prevention rate or total-cost analysis |
| Privacy considerations | Continuous analysis of school-camera footage raises questions about monitoring, retention and access | Screening changes how people and belongings are inspected at entry |
Questions schools should answer before buying detection technology
- Which rooms, approaches and entrances are actually covered, and can administrators document blind spots?
- What minimum distance, resolution, lighting and viewing angle are required for a reliable alert?
- How does the system behave when a weapon is partly hidden, held close to the body or visible for only a moment?
- Who verifies an alert, what image or video do they receive, and how is the event escalated if verification is delayed?
- What are the measured false-alert and missed-detection rates in conditions comparable to the school’s cameras?
- What independent evidence supports prevention or response benefits, rather than vendor claims alone?
- What are the full districtwide costs, including cameras, network upgrades, staffing, storage, training, maintenance and renewals?
- What data is retained, who can access it, and how long are student images and alert clips kept?
The bottom line
Antioch High’s system failure is clear: Omnilert did not recognize the weapon and did not notify police during the shooting. The reason is not settled. MNPS attributed the miss to distance and an image too unclear for activation, while Omnilert said the gun was not visible. The incident shows why camera AI is a coverage-dependent aid—not a guarantee—and why schools need independently measured performance, documented blind spots and response plans that do not depend on one alerting technology.
Quick Recap
Product prices and availability are accurate as of the date/time indicated and are subject to change. Any price and availability information displayed on Amazon at the time of purchase will apply.
