基于国产高分遥感的人工种植红树林种间分类方法研究——以广西茅尾海红树林为例

红树林的种间结构组成对红树林生态系统的健康和发展至关重要,而红树林种间分类问题一直以来都是基于遥感手段的红树林监测中的难点。针对该问题,以人工种植为特点的广西茅尾海红树林遥感种间分类为例,基于面向对象的分类思想,提出了一种现场样本与分割对象相结合的红树林种间分类方法。利用GF-2 PMS1高分辨率卫星遥感影像数据,开展了广西茅尾海红树林湿地典型植被精细分类和空间分布研究,并将分类结果与基于像素和传统面向对象SVM分类方法进行了对比。结果显示:总体上,面向对象分类方法更适合用于茅尾海红树林湿地典型植被分类;对于局部混生明显的区域使用基于像素SVM分类方法效果会更好;传统面向对象分类方法中将整个影像分割对象单元作为训练样本可能会在某种程度上造成负面影响。因此,使用文中提出的样本选择新方法进行面向对象分类精度最高,总体精度达到了93.13%,Kappa为0.89。     

Geospatial data mining for digital raster mapping

We performed an in-depth literature survey to identify the most popular data mining approaches that have been applied for raster mapping of ecological parameters through the use of Geographic Information Systems (GIS) and remotely sensed data. Popular data mining approaches included decision trees or “data mining” trees which consist of regression and classification trees, random forests, neural networks, and support vector machines. The advantages of each data mining approach as well as approaches to avoid overfitting are subsequently discussed. We also provide suggestions and examples for the mapping of problematic variables or classes, future or historical projections, and avoidance of model bias. Finally, we address the separate issues of parallel processing, error mapping, and incorporation of “no data” values into modeling processes. Given the improved availability of digital spatial products and remote sensing products, data mining approaches combined with parallel processing potentials should greatly improve the quality and extent of ecological datasets.     

Synergetic efficiency of Lidar and WorldView-2 for 3D urban cartography in Northeast Mexico

Three-dimensional urban cartography is needed for city changes’ assessment. The variety of studies using 3D calculations of urban elements grows each year. Building and vegetation volumes are necessary to assess and understand spatio-temporal urban changeable environments. However, there are technical questions as to which method can improve 3D urban cartographic accuracy. The innovative part of this current study is the creation of a six-band hybrid obtained from LIDAR and WorldView2 synergy. Two different enhancement algorithms demonstrated the most important spectral features for the urban development and vegetation classes. Results indicated an improvement in accuracy by up to 21.3%, according to the Kappa coefficient. Both infra-red band and intensity band were the most significant, according to the principal components analysis. The synergy delimited classes and polygons, as well as the direct display of information regarding heights of elements and improving the extraction of roads, buildings and vegetation classes.     

语义因子支持的多源POI分类信息一致化处理

为了解决网络POI分类异构导致多源POI数据匹配与整合困难的问题,该文利用分类特征词提取、特征词去重与优化等关键技术,构建POI分类的语义概念格,然后通过概念格之间的语义关联关系,实现多源异构POI分类体系的映射与转换。最后通过实验验证了该文方法的有效性,并将其成功应用于省级地理信息公共服务平台(政务版)数据更新。     

沈阳市建成区扩展动态监测

以辽宁省沈阳市为研究对象,以该地区1995年、2000年、2005年以及2016年不同时相的遥感影像为信息源。首先,利用ENVI影像处理软件进行数据预处理;然后,对沈阳地区土地类型进行MLC监督分类并评定分类精度;最后,采用分类后对比的方法并通过Arc GIS软件对沈阳建成区扩展情况进行研究。     

基于Sentinel-1B SAR数据的洪水提取和监测

洪涝灾害是我国最严重的气象灾害之一,及时准确的洪灾监测是防灾减灾的重要前期工作和基础。本文利用sentinel-1B雷达数据,以黑瞎子岛为研究区,联合使用OSTU阈值分割法和随机森林面向对象分类法针对像素统计单波形、双波形、多波形SAR影像提取洪水要素,实现对洪灾淹没面积的时序监测,为灾情监测提供数据和技术支撑。     

基于改进BP神经网络的海底底质分类

通过采用遗传算法优化神经网络初始权值的方法,将GA算法与BP神经网络有机结合,应用于海底底质分类。基于多波束测深系统获取的反向散射强度数据,应用改进的BP神经网络分类方法,实现对海底基岩、砾石、砂、细砂和泥等底质类型的快速、准确识别。通过实验比较,GA-BP神经网络分类精度明显高于BP神经网络,证明了该方法的有效性和可靠性。     

水产养殖遥感监测及信息自动提取方法研究

以海南省文昌地区为例,在沿海地区尝试利用遥感监测的手段提取水产养殖地块和面积.采用面向对象的分类方法进行监测,取得了理想效果,同时也提出了提高分类精度的建议.     

Classifier ensembles for land cover mapping using multitemporal SAR imagery

SAR data are almost independent from weather conditions, and thus are well suited for mapping of seasonally changing variables such as land cover. In regard to recent and upcoming missions, multitemporal and multi-frequency approaches become even more attractive. In the present study, classifier ensembles (i.e., boosted decision tree and random forests) are applied to multi-temporal C-band SAR data, from different study sites and years. A detailed accuracy assessment shows that classifier ensembles, in particularly random forests, outperform standard approaches like a single decision tree and a conventional maximum likelihood classifier by more than 10% independently from the site and year. They reach up to almost 84% of overall accuracy in rural areas with large plots. Visual interpretation confirms the statistical accuracy assessment and reveals that also typical random noise is considerably reduced. In addition the results demonstrate that random forests are less sensitive to the number of training samples and perform well even with only a small number. Random forests are computationally highly efficient and are hence considered very well suited for land cover classifications of future multifrequency and multitemporal stacks of SAR imagery.