Very important part in algorithm evaluation is the quality of testing images and/or videos. Larger number of images and/or videos, containing different scenarios and surroundings gives the better quality of the evaluation process.

As mentioned in section Smoke detection two types of wildfire smoke detection procedures could be defined:

• image based wildfire smoke detection and
• video base wildfire smoke detection.

Because of that we have formed two bases:

• wildfire smoke image database and
• wildfire smoke video database (or more preciously a wildfire image series database).

Both of them could be used freely for wildfire smoke detection algorithms development and/or testing. Although most of today's algorithms are video or image sequence based algorithms the single image base wildfire smoke detection is a challenging research topic, so we have also included in our databases a collection of single wildfire smoke images.

Registered users could upload their images, image sequences or videos, too, so our idea is to create a comprehensive image base of wildfire smoke images, image sequences or videos available to all wildfire smoke detection and recognition researchers.

• Image database
  
• Video database

A part of the video cllection used for the evaluation of "Adaptive estimation of visual smoke detection parameters based on spatial data and fire risk index" can be found at the following link:

• Adaptive estimation of detection parameters - video database