Fire & Smoke Detection

Principle of the AI Task

The "Fire and Smoke Detection" task is designed to automatically detect fire and smoke in real time based on surveillance camera data.

The system works by counting the number of frames that fire or smoke is detected within a user-defined detection timeframe. The monitored area can be either the entire camera view or a specific region of interest (ROI).

When the ratio of frames with fire or smoke to the total number of frames in the timeframe reaches or exceeds the detection rate threshold set by the user, the system will trigger an alert.

Alerts can be sent in various forms, depending on user configuration. The software allows users to flexibly customize how they want to receive alerts.

Application Fields

This task is mainly used in the following scenarios:

• Outdoor and Open Area Fire AlertsThe task can be effectively applied to monitor and alert for forest fires, fires in industrial zones, or wide/open spaces such as storage yards and outdoor warehouses. It enables fire detection from a distance without requiring direct human presence.

• Early Detection of Fire and SmokeThe AI system can identify visual signs and features of fire/smoke from the early stages (e.g., small size, before spreading), outperforming traditional sensor systems that rely on smoke concentration or temperature. Once detected, alerts can be sent to monitoring centers, fire response teams, or responsible personnel, enabling a rapid response to minimize damage.

• Flexible Integration with Existing Fire Alarm Systems It works like a smart fire detection sensor that can be connected to traditional or addressable fire alarm systems using image-based AI analysis, enhancing detection accuracy and response capability.

  And other fire alert–related requirements.

AI Task Setup

To create a fire and smoke detection task:

1. Select the task type Fire Smoke Detection.

2. Objects: Choose fire and/or smoke. Press Ctrl to choose multiple objects.

3. Detection Timeframe (s): The duration (seconds) that the system will analyze from the moment it detects fire or smoke. This number of seconds will then be converted into the equivalent number of frames.

   Example: If the camera has 10 FPS and the detection timeframe is 8 seconds. Then, the total frames will be 8s x 10FPS = 80 frames. This means that from the moment fire/smoke detected, the system will continue to analyze for an additional 80 frames before making a conclusion.

4. Detection Rate (s): The minimum ratio between total frames with fire/smoke vs the total frames. When the actual ratio is greater than or equal to the minimum ratio, the system will trigger an event

   Example: Detection rate = 40%, meaning that if there are at least 32 frames with fire/smoke out of 80 consecutive frames, the system will trigger an event

5. Repeat Detection Every (s): The time (in seconds) to pause before sending the next event.

6. ROI (optional): Select Rectangle or Polygon, then click Add ROI to draw the monitoring area on the camera (if not drawn, the entire frame will be monitored by default).

7. Click Save Task to complete.

Characteristics of the AI Model

The AI model used in this task has several important characteristics to note:

Model Accuracy

The task uses a fire and smoke detection AI model with an accuracy of ≥ 95%, under the following conditions:

Object	Minimum Size Relative to Frame	Operating Weather	Day/Night Performance
Fire	0.1%	Works well in dry conditions; may be affected by rain or fog	Works both day and night (in color). Night accuracy is ~70–80% of daytime.
Smoke	1.5%	Works well in dry conditions; may be affected by rain or fog	Hardly detectable at night.

Realistic of Fire and Smoke

• The model is trained on real fire and smoke data. Therefore, similar visual sources such as lighters, fire extinguisher smoke, stage effects, clouds, fog, still images, or similar artificial fire/smoke are either excluded or detected with low confidence. This helps reduce false alerts.
• The model analyzes a set of frames to verify if fire or smoke is real. It also combines this with user-configured parameters before triggering an event. Therefore, it typically takes under30 seconds for the AI to gather sufficient data and generate a reliable event.

Camera Quality

• Image Clarity: Lower-quality cameras (low resolution, poor focus) reduce the model’s detection accuracy.

• Lighting Conditions: Bright light or glare may affect detection. Cameras with suitable light sensitivity and good image quality are recommended.

• Night Vision: To ensure effective nighttime detection, cameras should support color infrared (IR) imaging.

• Camera Installation Position

  • Ensure the monitored area is unobstructed (no trees, covers, or fabric blocking view), so that fire or smoke is visible.
  • The camera should face directly towards the protected area, avoiding unrelated zones to improve detection accuracy.
  • Position the lens as close as possible to the area to be monitored, with proper focus to avoid blurriness that could reduce algorithm sensitivity.
  • Avoid placing the camera where strong natural or artificial light directly hits the lens.

• Environment

  • Low contrast between fire/smoke and the background reduces detection accuracy. In such cases, a larger or closer fire is needed for reliable detection.

    example

    Low Contrast: Fire color blends with background

    

    High Contrast: Fire color stands out clearly

    

  • When a fire occurs in the protected area, the camera angle should capture detailed fire/smoke visuals. The background should avoid colors similar to fire (red, orange) or smoke (black, white). If unavoidable, add artificial contrasting colors in the background to enhance focus and contrast.

  • It is recommended to use the camera's auto-white balance feature to ensure accurate environmental color representation.

Notes

During installation, setup, and usage, some issues may arise that require attention as follows:

• Red or yellow flags can sometimes be mistaken for fire if the settings are too sensitive. Adjust the task settings parameters.
• Fog and artificial smoke can sometimes be mistaken for real smoke if the settings are too sensitive. Adjust the task settings parameters.
• Rain can reduce recognition capability. Find methods to improve camera visibility.
• Darkness can reduce recognition capability. To increase accuracy, choose a camera with good color light sensitivity. Nighttime always yields more limited fire detection results than daytime. Smoke detection is difficult at night.
• When strong winds distort the image of the fire or reduce the density of the smoke, the AI's detection capability decreases. The detection distance may be shortened. AI will still be able to detect fires and smoke according to the announced frame rate, but the accuracy will be much lower than the advertised accuracy.
• Intensity of Fire and Smoke: If the movement of fire and smoke is almost static and not clear enough, the AI's detection capability will decrease because the model has an algorithm that distinguishes it from static fire and smoke images.