多源遥感汇报.pptx

影像与激光雷达数据的城市地物信息提取;1.研究区及数据;2.研究方法;2.1数据预处理;获取地物类型最佳分割尺度：如图5所示的分割质量曲线图，其中建设用地包括建筑物、道路、空地；林地包括树木及草地。从图中可看出随着分割尺度的增大，p值减少，r值增加，过分割现象减少，欠分割现象增多，而 m2为这两种度量的加权和，不存在偏向性。因此最佳分割尺度一般取m2最大值处，若 m2近似则选取p值较大处，得出各类地物类型的最佳分割尺度。树木与草地为33，道路与空地为45，阴影为18。;2.3对象分类; 特征选择后采用两步法提取城市地物，首先采用多分类器组合(K近邻算法、神经元网络及SVM_RBF)对城市地物进行分类，得到如图6所示的分类结果。由于城市地区存在高层建筑及树木，分类受阴影的影响较大，因此定本文在得出初步分类结果后采用易康5.0将阴影区域进行分割，并基于规则将阴影区域依次分为：阴影下植被、阴影下建筑物、阴影下道路、阴影下空地、纯阴影5类。 图7为A区最终分类结果，利用混淆矩阵法进行分类精度评价，总体精度为93.1%，如表2所示 ;;2.4 方法检验;3 结束语;Monitoring coal fires in Datong coalfield usingmulti-source remote sensing data;Abstract:;The Datong coalfield is located in northern Shanxi Province, China approximately from 39°52′ to 40°10′north latitude and 112°49′32″ to 113°9′30″ west longitude。 It has a complex terrain with an average altitude of more than 1200m. The studied area is located in the Majiliang mining area Coal fires mainly occur in the No. 2 Jurassic coal seams in the mining area, 30m to 130m below the surface, with an average thickness of about 1m。;3 Multi-source remote sensing monitoring;3.1 Coal fire monitoring using Landsat thermal infrared band; (a) R(Band 5), G(Band 4) and B(Band 3) composite images with 15 m spatial resolution  (b)?(f)temperature distribution retrieval by Landsat thermal infrared band with 60 m spatial resolution;3.2 Coal fire monitoring using UAVBy contrast, compared with satellite remote sensing, UAV has many adva-ntages. It is more flexible in terms of working time and region, has higher spatial resolution (more than 0.2 m), and is cost effective. It provides much better image data for ground fissures.;Fig4 UAV image with 0.2 m spatial resolution able to cature ground fissure in coal fire regions;According to the texture information, linear feature,and brightness of the ground fissures, a knowledge model was established to facilitate the automatic extraction of ground fissures. The steps are as follows. 1)Occurrence-based variance, cooccurrence based variance, data