The requirements for cameras that will work with the Fire detection and Smoke detection modules are shown in the following table.
Camera | - It is recommended to use color cameras. With black and white cameras, the recognition quality may be much worse
- Resolution should be at least 640x360 pixels
- Number of frames: the response rate of the detection module depends on the number of frames per second, by default, it is 1 per every 10 seconds (in most cases, it is enough to detect a fire/smoke that lasts more than 1 minute)
|
Lighting | - Fire/smoke should be visually separated from the background
|
Object images | - The minimum area of fire/smoke in the frame depends on the neural network used. For a standard neural network (see Configuring the Fire detection and Smoke detection modules), the area of fire/smoke should be at least 10% of the frame. In some cases, when the fire is well contained, it may be sufficient for a detection tool that the width/height of the fire zone is 1-3% of the width/height of the frame.
|