Upgrade Your CCTV With AI Fire Alert

Turn any CCTV into a smart AI fire detector that watches your camera feed in real time and pushes an instant alert to your phone the moment flames are spotted — all without writing a line of code. Works with USB, CSI, ONVIF, or RTSP cameras, runs on Grablo-supported devices, and even on a laptop with a built-in webcam if you just want to try it out.

⚠️ Important safety note: This AI is designed to support your existing fire detection system, not replace it. Always keep certified smoke alarms and fire detectors in place — treat this project as an extra alert channel, never as your primary safeguard.

Hardware:

1. Windows PC, Mac, Raspberry Pi, or any other Grablo-supported device
2. Camera — USB, CSI, ONVIF, or RTSP (laptop webcam works too)
3. Smartphone for receiving push notifications
4. Optional: USB video capture adapter if you're using an old analog CCTV without networking

Software:

1. Grablo — No-Code IoT Platform (grablo.co)

Want to skip the build and just run it? Copy the project from the Grablo Gallery:

1. Download and install Grablo software on your device from grablo.co/download
2. Get this project from the Grablo Gallery
3. Open the Grablo app at app.grablo.co in your browser
4. Configure your camera in Settings → Camera → Edit (every CCTV is different — pick the type that matches yours and enter the address or index)
5. Install the Grablo app on your phone and sign in with the same account to receive push alerts
6. Connect to your device and hit RUN!

If you'd rather build it from scratch, follow the steps below.

Create a new project at app.grablo.co, name it "AI Fire Alert," and select your device. Then create a dashboard and add the following widgets: a Camera widget for the live video feed, and a Label widget bound to the Fire Probability variable with the unit set to percent. Switch to the mobile layout and resize the widgets so the dashboard reads cleanly on your phone too.

This project uses two controls. The first one starts the AI: a Once condition fires it at launch, and an AI Analysis action creates a new AI Analyzer with the Fire Detection model bound to your camera. The Add Analysis command writes the model's detection result into a Fire Probability variable, and a Start Analysis command (added by duplicating the Add Analysis action and changing the command) actually kicks off the AI on the live feed.

The second control handles the alert. A Compare condition watches the Fire Probability variable and triggers whenever it goes above 50, firing a Push Notification action with your alert title and message. A Delay action then pauses 10 seconds — so as long as the probability stays above 50%, you keep getting a fresh push every 10 seconds until the fire clears.

The camera is intentionally left unconfigured because every CCTV is different. Go to Settings → Camera → Edit and pick the right type for your setup:

1. USB webcam or analog CCTV with a video capture adapter: CSI/USB type, index 0
2. Network IP camera: ONVIF or RTSP type with the camera's address and credentials

While you're there, pick the AI mode based on your device — Fast for low-power devices like a Raspberry Pi, Accurate for more powerful machines.

Launch Your Project:

1. Open the Grablo app and select your project
2. Connect to your device
3. Hit RUN!
4. Make sure the Grablo app is installed on your phone and you're signed in with the same account

Expected Results:

1. The dashboard shows your live camera feed and a Fire Probability readout
2. When flames appear in view, the probability climbs in real time
3. Once it crosses 50%, a push alert lands on your phone
4. While the fire persists, you keep getting a push every 10 seconds
5. Tapping any notification opens the live camera stream so you can verify the situation immediately

Expand Your Project

1. Lower the 50% threshold for more sensitive areas, or raise it where false positives are common
2. Shorten the 10-second delay for higher-risk zones, or lengthen it to reduce notification fatigue
3. Add a Send Email action alongside the push for a backup notification channel
4. Trigger a smart plug or relay to cut power to the room when fire is detected
5. Combine multiple cameras (kitchen, garage, server room) into one fire-monitoring dashboard

Troubleshooting:

1. Camera feed not showing: double-check Settings → Camera → Edit — the project ships without camera credentials, so you need to enter your CCTV's details manually
2. Fire Probability stays at 0: make sure the AI Analyzer started successfully and the camera feed is actually delivering frames
3. No push alerts arriving: install the Grablo app on your phone, sign in with the same account, and allow notifications
4. Too many false alarms: raise the 50% threshold, or switch the AI mode to Accurate
5. AI is slow: switch the AI mode to Fast