Airborne near-real-time monitoring of assembly and parking areas in case of large-scale public events and natural disasters

A critical requirement for an effective and coordinated response by public entities tasked with management, security, and relief during large-scale public events or natural disasters is the availability of current situational information. However, today there is a lack of comprehensive operational systems allowing a near-real-time (NRT) collection, visualization, and provision of situational information for larger areas. In this study a methodological framework is proposed, which allows an NRT extraction and visualization of situational information based on aerial image acquisition. The framework combines digital image analysis using a generic supervised information extraction approach based on statistical modeling with a downstream web-based visualization component realized through an automatic update of web services. Even though being applicable for different scenarios, the workflow will be demonstrated for the specific use-case of a NRT monitoring of open spaces including assembly and parking areas. Compared to other approaches, image analysis results indicate a high robustness and a low demand for computational power sources (7 seconds per image). Due to a high degree of automation, the proposed workflow contributes to a NRT ‘end-to-end’ monitoring system, which was developed within the VABENE (German acronym for ‘traffic management under large-scale public events and disaster conditions’) project covering all parts from the acquisition of raw aerial imagery to the dissemination of information products to end-users.     

采用非线性决策树的学生课堂教学满意度研究

学生反馈是评估高等院校课堂教学质量的重要指标。目前,对学生反馈的问卷仅进行主观理解和简单统计,无法提供准确定量的分析和支持依据。使用非线性决策树,对近3年本科必修双语课程《数字图像处理》的学生评教问卷进行数据挖掘,首先将其分成3类和10个不同输入,然后通过数据预处理、模型选择和建模,最后构建树状模型对其进行分析。分析结果符合对于该课程学生反应和争议较大的问题预期,为课程设计提供定量有效的教学分析工具。     

基于ENVI 的唐山湾三岛土地利用遥感分类方法的比较分析

对唐山湾三岛2010年10月10 m分辨率的SPOT5多光谱数据源,采用不同分类方法进行识别和判断,并对比不同分类器在遥感影像分类中的应用效果和分类精度。有针对性地探究海岛土地利用遥感分类过程中不同方法的优劣,获取最适于岛陆地区土地利用的遥感分类方法。根据土地利用现状分类标准(GB/T21010-2007)和海岛陆域土地利用类型划分的相关规定,将唐山湾三岛主要分为滩涂、裸地、林地、草地、居住区、内陆水体和潮间带(潮水覆盖区)6类。并分别构建结合人为控制的非监督分类、监督分类和基于专家知识的决策树分类系统,参照更高分辨率影像、先验知识和野外调查资料,评价分类结果与实地调查结果的吻合程度,最终通过总体分类精度和Kappa系数等指标对各分类器精度进行评价和对比分析。     

结合地形因子与分层策略的喀斯特地区无人机影像分类

西南喀斯特山区地形起伏较大,地物分布较为破碎,致使传统的光谱特征一次分类方法的精度较低。本文基于高分辨率无人机正射影像和地形指标,充分利用无人机遥感影像空间特征、光谱特征、纹理特征及地形特征,采取面向对象CART决策树算法与分层策略提取了研究区土地覆盖类型。研究表明,结合空间地形因子和分层策略的方法减少了破碎区地物间的相干扰,故具有较高的分类精度,总体分类精度达91.2%,Kappa系数为0.87,较传统一次分类精度提高了9.8%,Kappa系数提高了0.13。该方法对西南喀斯特地区土地覆盖解译精度较好,可为土地利用监测提供参考。     

三维辅助决策平台功能设计及数据建设研究

三维数据由于其直观、精细的特性成为数字城市建设中不可或缺的部分,三维辅助决策平台也成为近年来信息化建设的重要方面。本文从三维辅助决策平台建设时的功能设计和数据建设两个方面进行阐述,对其中运用的技术进行研究。最后,给出了针对不同应用领域系统建设的示例。     

分类器和时相结合的流域下垫面分类方法

文章探讨提高卫星遥感大范围流域下垫面分类方法:通过集合贝叶斯分类器和决策树分类器的优势,充分利用TM影像覆被信息,结合影像时相动态信息以获得分类准确的土地覆盖/利用类型;再结合DEM生成的坡度信息得到下垫面类型,最终确定水文地理单元.以河南省的东湾流域为例进行验证,结果表明:贝叶斯法和决策树法分类各有优势,两者结合可以获取更准确的土地覆盖/利用分类结果,辅以时相类信息可以进一步修正类别间的混淆.     

人工神经网络和决策树模型在滑坡易发性分析中的性能对比

机器学习模型广泛应用于区域性滑坡易发性分析。模型的选择关系到评价结果的可信度、准确率和稳定性。现有滑坡易发性分析模型对比研究侧重模型的预测精度。模型的稳定性和数据量敏感性对机器学习模型的性能评估同样非常重要。本文以福建省南平市蔡源流域为研究区,以四川省绵阳市北川县为验证区,从预测精度、稳定性和数据量敏感性3个方面深入对比BP（Back Propagation）人工神经网络模型和CART（Classification and Regression Tree）决策树模型在滑坡易发性分析中的效果,主要结论如下:① 在逐渐增加一定数量训练样本的过程中,BP人工神经网络模型预测精度的增长率更高。在蔡源流域内,当训练样本数量增加10 000时,BP人工神经网络模型的预测精度上升5.22%,CART决策树模型的预测精度上升2.11%。② BP人工神经网络的预测精度高于CART决策树模型,且较为稳定。在100组数据集上,BP人工神经网络模型验证集预测精度的均值和验证集滑坡样本预测精度的均值分别为81.60%和84.86%,高于CART决策树模型的72.97%和76.59%。与此同时,BP人工神经网络模型对应预测精度的标准差分别是0.32%和0.37%,小于CART决策树模型的0.35%和0.67%。③ BP人工神经网络模型分析的滑坡易发区相比CART决策树模型,更接近实际滑坡的空间分布。最后,北川县的验证实验也出现了相同的现象。     

基于GIS与SDM技术的可视化空间数据分类研究

提出将GIS与可视化空间数据挖掘技术之集成的基本框架。在此基础上,基于VisualC++6.0和Ma-pObject2.0组件技术设计和开发了一个可视化交互空间数据挖掘分类系统,系统采用决策树方法和贝叶斯网络作为数据挖掘方法的基本算法,采用训练与学习相结合实现空间数据的分类。文中用实例数据对系统性能、算法和规则有效性进行了验证。结果表明,该系统是一个适用的、可扩展的可视化交互空间数据挖掘工具,系统能够实现数据挖掘实时动态的交互控制,实现了数据挖掘过程的可视化、挖掘模型的可视化和结果的可视化显示、可视化思考、可视化分析与评价。     

甘南州国土空间规划辅助决策系统的构建与实现

基于“天地图·甘肃”地理信息公共服务平台提供的地图API功能,在 “天地图·甘南”州级节点的基础上,整合甘南州国土空间规划相关数据和评价模型,采用可视化B／S前后端分离架构,矢量瓦片索引和微服务等技术,搭建了甘南州国土空间规划辅助决策系统,并通过系统平台实现了资源浏览、数据查询、数据统计、占地分析、规划冲突分析、数据大屏等辅助决策功能,为建设项目选址、用地审批、规划审查、土地储备与开发等提供决策服务。     

Holistic approach of GIS based Multi-Criteria Decision Analysis (MCDA) and WetSpass models to evaluate groundwater potential in Gelana watershed of Ethiopia

Appropriate quantification and identification of the groundwater distribution in a hydrological basin may provide necessary information for effective management, planning and development of groundwater resources. Groundwater potential assessment and delineation in a highly heterogeneous environment with limited Spatiotemporal data derived from Gelana watershed of Abaya Chamo lake basin is performed, using integrated multi-criteria decision analysis (MCDA), water and energy transfer between soil and plant and atmosphere under quasi-steady state (WetSpass) models. The outputs of the WetSpass model reveal a favorable structure of water balance in the basin studied, mainly using surface runoff. The simulated total flow and groundwater recharge are validated using river measurements and estimated baseflow at two gauging stations located in the study area, which yields a good agreement. The WetSpass model effectively integrates a water balance assessment in a geographical information system (GIS) environment. The WetSpass model is shown to be computationally reputable for such a remote complex setting as the African rift, with a correlation coefficient of 0.99 and 0.99 for total flow and baseflow at a significant level of p-value<0.05, respectively. The simulated annual water budget reveals that 77.22% of annual precipitation loses through evapotranspiration, of which 16.54% is lost via surface runoff while 6.24% is recharged to the groundwater. The calibrated groundwater recharge from the WetSpass model is then considered when determining the controlling factors of groundwater occurrence and formation, together with other multi-thematic layers such as lithology, geomorphology, lineament density and drainage density. The selected five thematic layers through MCDA are incorporated by employing the analytical hierarchy process (AHP) method to identify the relative dominance in groundwater potential zoning. The weighted factors in the AHP are procedurally aggregated, based on weighted linear combinations to provide the groundwater potential index. Based on the potential indexes, the area then is demarcated into low, moderate, and high groundwater potential zones (GWPZ). The identified GWPZs are finally examined using the existing groundwater inventory data (static water level and springs) in the region. About 70.7% of groundwater inventory points are coinciding with the delineated GWPZs. The weighting comparison shows that lithology, geomorphology, and groundwater recharge appear to be the dominant factors influence on the resources potential. The assessment of groundwater potential index values identify 45.88% as high, 39.38% moderate, and 14.73% as low groundwater potential zones. WetSpass model analysis is more preferable in the area like Gelana watershed when the topography is rugged, inaccessible and having limited gauging stations.