Improving the accuracy of image-based forest fire recognition and spatial positioning

作     者：JIANG LiLi 1,QI QingWen 1,ZHANG An 1,GUO ChaoHui 2 & CHENG Xi 1,3 1 Institute of Geographical Sciences and Natural Resources Research,Chinese Academy of Sciences,Beijing 100101,China 2 China Center for Resources Satellite Data and Applications,Beijing 100094,China 3Graduate University of Chinese Academy of Sciences,Beijing 100049,China 

作者机构：Institute of Geographical Sciences and Natural Resources Research Chinese Academy of Sciences Beijing China China Center for Resources Satellite Data and Applications Beijing China Graduate University of Chinese Academy of Sciences Beijing China 

出 版 物：《Science China(Technological Sciences)》 (中国科学（技术科学英文版）)

年 卷 期：2010年第53卷第S1期

页      面：184-190页

核心收录：

学科分类：08[工学] 080203[工学-机械设计及理论] 0802[工学-机械工程] 

基　　金：supported by the National High-Tech Research and Development Program of China("863"project)(Grant No.2006AA06Z418) 

主　　题：forest fire monitoring spatial positioning accuracy improvement 

摘      要：Forest fires are frequent natural *** is necessary to explore advanced means to monitor,recognize and locate forest fires so as to establish a scientific system for the early detection,real-time positioning and quick fighting of forest *** paper mainly expounds methods and algorithms for improving accuracy and removing uncertainty in image-based forest fire recognition and spatial ***,we discuss a method of forest fire recognition in visible-light *** are four aspects to improve accuracy and remove uncertainty in fire recognition:(1)eliminating factors of interference such as road and sky with high brightness,red leaves,other colored objects and objects that are lit up at night,(2)excluding imaging for specific periods and azimuth angles for which interference phenomena repeatedly occur,(3)improving the thresholding method for determining the flame border in image processing by adjusting the threshold to the season,weather and region,and (4)integrating the visible-light image method with infrared image ***,we examine infrared-image-based methods and approaches of improving the accuracy of forest fire recognition by combining the spectrum threshold with an object feature value such as the normalized difference vegetation index and excluding factors of disturbance such as interference signals,extreme weather and high-temperature ***,a method of visible analysis to enhance the accuracy of forest fire positioning is examined and realized;the method includes decreasing the visual angle,selecting central points,selecting the largest spots,and judging the selection of fire spots according to the central *** studies are examined and the results are found to be satisfactory.