Auto-identification of forest fire-points in NOAA images based on neural network.

Autor: Yitong, Liang, Jianglin, Hu, Liangming, Liu, Ping, Xie
Zdroj: Geo-Spatial Information Science; Sep2001, Vol. 4 Issue 3, p68-72, 5p
Abstrakt: Identification of forest fire-points in NOAA images in the basis of monitoring forest fire using NOAA satellite data. Traditional visual interpretation is difficult to settle for auto identification with computer. The artificial neural network technique provides a new means for solving this problem. In this paper, the principles and method of using neural network technique to automatically identify fire-points in NOAA images are discussed and the test in the range of Hubei province is presented. The result of the test shows that the disciplined neural network has collected the character of fire-points and has ability to identify fire-points in NOAA images. Comparing neural network with visual interpretation, the conclusion is drawn that by using neural network the purpose of auto-identification of forest fire-points in NOAA images can be realized with the almost same precision. [ABSTRACT FROM AUTHOR]
Databáze: Complementary Index
Externí odkaz: