Requirements and recommendations for the Fire and Smoke Detection module🔗

Hardware and software

Warning

The Eocortex Neural Networks package must be installed before it will be possible to use neural networks-based features of the module.

For the Based on neural networks operating mode, the following are required:

  • A processor that supports AVX instructions;

  • An NVIDIA video card (GPU) with the computation capacity index of at least 6.5 and with at least 4 Gb of memory; the parameters and performance of the video card must be similar or better than those of NVIDIA GTX 1650 Ti model;

  • Version of the video card driver at least 460;

  • Swap file at least half of the total RAM size.

If the package will be installed on a virtual machine, it may additionally be required to:

  • Enable support for AVX instructions in the guest machine settings;

  • Use GRID drivers for GPU virtualization.

Warning

Eocortex must use video cards selected for running neural networks in monopoly mode. It is not allowed to use such card for other applications or tasks that consume GPU resources, including for displaying video. Simultaneous use of a video card for several tasks may lead to incorrect system operation: from analytics performance degradation to server instability.

Warning

The neural network works with the 64-bit version of Eocortex only.

Warning

When upgrading Eocortex to another version, it is necessary to also upgrade the Eocortex Neural Networks package to the corresponding version.

Image

  • Image and background must be static: the camera shall be rigidly fixed, there shall be no constantly moving objects in the frame.

Video stream

  • Minimum permissible resolution of the frame is 400x300 pixels.

  • Minimum permissible frame rate is 15 and 5 frames per second for fire detection and smoke detection modes respectively.

Lighting and image quality

  • The illumination of the detection area must not change drastically (for example, when the light is switched on, when the camera switches to night mode, etc.).

  • In the smoke detection mode, it is necessary to ensure minimum required illumination and to avoid that the direct light shines on the lens.

Scene and camera position

  • The camera shall be placed at the angle of 0 — 70 degrees in reference to the level surface.

  • The objects of potential hazard must be located in the line of site of the camera. That means that they must not be blocked by other objects.

  • In the camera field of view there must be no “benign” sources of smoke and fire, such as furnaces, steam boilers or pipes, welding equipment etc.

  • The dimensions of the objects to be detected (smoke and fire areas) must be no less than 10% of each linear measure of the frame.

Object size

To successfully detect objects in the frame, their sizes must conform to the following ratios relative to the frame size:

Smoke

  • In forested areas, it must occupy at least 4% of the width and 3% of the height.

  • In urban or indoor environments — at least 12% of the width and 17% of the height.

Fire

  • In urban environments or indoors, it must occupy at least 5% of the width and 6% of the height.