Application of colorimetry in neural network methods of fire detection in woodlands

Currently, neural network methods of fire detection have been used to monitor fires in forests. To date, such systems developed as the Prometheus project, Fire Video Detector, and Artificial Intelligence University method. These make it possible determine a with an accuracy more than 90 %, for which combination recurrent light-line networks is used. The article proposes method improving efficiency determining forests based on computer colorimetry. use this makes increase detecting when using multiple cameras video surveillance system. Thus, presents comparison performance convolutional without colorimetric module. According results, work has increased by 20 %.