基于支持向量机的遥感图像建筑物识别与分类方法研究

高分辨率遥感影像可以更精细地描述地物目标的几何特征、空间特征和纹理特征等信息,在各个领域中都得到广泛的应用。建筑物作为地物信息分类中的主要部分,是地形图成图的主要组成元素,对建筑物的识别与提取,直接影响到地物测绘的自动化水平,对它的识别和定位可以为特征提取、特征匹配、图像理解、制图和作为其他目标的参照体有重要的意义。针对建筑物的遥感影像特征,研究了支持向量机分类器(SVM)在建筑物识别与分类中的应用,提出了一种交叉验证的方法对参数敏感度进行分析,通过使用GridSearch算法确定模型参数设置的最优方案,并对分类结果中建筑物进行轮廓提取。通过实验表明,优化后的SVM算法对建筑物的分类精度达到90%,对比随机森林算法、最近邻分类器优势非常明显。     

基于随机补片和DeepLabV3+的建筑物遥感图像变化检测

为有效解决传统遥感图像变化检测预处理复杂的问题,提出一种基于随机补片和DeepLabV3+的建筑物遥感图像变化检测方法。以ResNet50特征提取网络为基础,创建DeepLabV3+语义分割网络,并在图像和标签中创建大小为224像素×224像素的随机补片作为网络输入,训练建筑物提取网络;修改建筑物提取网络输入层为6通道,通过矩阵运算将两期遥感图像转换为一幅6通道非RGB图像,利用转换后的非RGB图像进行网络训练并验证变化检测精度。实验1利用ENVI5.3软件,采用马氏距离法进行变化检测;实验2采用改进的U-Net网络和随机补片,完成网络训练和精度验证;实验3使用实验2的训练数据和验证数据,采用随机补片和DeepLabV3+网络进行变化检测网络训练及精度验证。实验结果表明,该方法实验1、实验2、实验3建筑物变化检测平均交并比分别为24.43%、83.14%、89.90%,边界轮廓匹配分数分别为61.47%,80.24%、96.51%。     

山丘区小流域地形空间分析及数字信息提取

山丘区小流域地形特征及数字水系的自动提取为山洪防治提供了必要的数据准备.本文采用地形特征自动提取软件包DigitalHydro,对山区小流域地形及水系基本信息进行了提取试验.研究中,地形数据引用栅格型DEM数据SRTM,水平分辨率接近90m,研究对象为浙江省姜湾水文实验流域.该流域拥有3个流量站,提取的集水面积分别为20.64km2,10.21km2,1.31km2,误差分别为-1.2%,0.1%和-3.0%.分析显示,流域地形总体起伏较大,平均坡度为33%,现有DEM分辨率能满足流域水系等基础信息的提取.但在河谷地带存在洼地,造成提取的水系与实际情况存在一定差异,提取水系时,局部需要引入空间分辨率更为细致的地形信息.     

基于SAR图像的震害建筑物信息提取方法综述

地震是对人类生命和财产威胁最大的自然灾害之一,大地震往往引起大量建筑物倒塌,从而造成大量人员伤亡和财产损失。震后快速准确地评估建筑物损毁情况,有利于合理安排资源进行救援和灾后重建。合成孔径雷达(SAR)遥感凭借其全天时、全天候工作能力,在评估建筑物震害信息中发挥了重要作用。本文将从SAR传感器的发展历程入手,介绍SAR提取建筑物震害信息的方法,并针对各个方法的优缺点和存在的问题,指出可行的解决方案,这有利于根据实际情况选择合理的方法,从而快速准确地获取震害信息。最后展望了SAR图像提取震害建筑物信息的发展趋势。     

基于机载LiDAR数据的海地地震震后建筑物信息提取与三维建模

机载激光雷达技术(LiDAR)可以直接获取地表高精度三维信息,载有LiDAR设备的飞机可深入到震后交通遭受严重破坏的重灾区,快速对大范围区域进行数据采集及数据分析,为灾情信息获取与评估以及震后救援提供技术支撑。本文对获得的海地雅克梅勒(Jacmel)地区震后LiDAR点云数据进行了处理和分析,通过提取建筑物矢量,生成数字地表模型(DSM),探索了震后建筑物信息提取及三维建模方法,创建了真实可量测的三维建筑物模型。结果表明,由于雅克梅勒地区距离震中较远、建筑物破坏程度较低,震后大部分建筑物完好,基于激光点云数据的震区建筑物三维重建效果较好。     

一种机载雷达点云数据的快速分类方法

机载激光雷达扫描技术可以以点云形式快速获取地形表面高精度三维信息。基于激光雷达扫描数据及建筑物本身的拓扑信息就可以对建筑物进行精确的重建,而重建中最关键的技术是对点云数据进行分类,进而进行地物识别。对大规模三维点云数据进行快速分类,提出一种采用区域分割结合基于最小二乘平差的多项式拟合方法,将大量离散的三维点云分割后进行多项式拟合,并将二维数据分类转化为一维数据分类。在分类的基础上,将建筑物几何规则作为约束条件提取了房屋边缘。实验分析表明,该方法既能去除多余噪声,又能有效保留特征点,分类的总误差率低于3%。     

Spot图像上环形构造的提取和分类

卫星图像上环形构造的提取主要包括三个步骤:首先是轮廓的提取;其次是轮廓的进一步处理,其中包括轮廓的分解,把曲线分解为次圆元素。对每个次圆元素进行Hough变换等处理;最后计算所提取构造的各种参数。     

波谱分析法在油气地球化学勘探中的应用研究

利用空间地球化学数据波谱分析技术,可以获得更为丰富的地球化学信息,以便从多个层面认识研究区的地球化学特征,从而能把握各种信息中所包含的与油气相关的实质性内容,较为准确地提取油气异常信息,客观地预测油气远景区.研究表明,波谱分析的低频分析结果通常给出地球化学场的主特征轮廓,中频滤波结果与油气田有较好的吻合性.高频滤波结果反映的是难以认识的浅表效应和噪声信息.很好地利用低频和中频滤波结果,结合不同频率域的滤波结果,能较为准确地提取油气异常信息.     

塔里木盆地南缘喀拉米兰河克里雅河流内流区近30a来的冰川变化研究

对1999年的喀拉米兰河-克里雅河流内流区的Landsat ETM+影像运用非监督分类、监督分类,雪盖指数域值法和比值域值法提取其中176条冰川的边界信息,并与目视解译结果进行定量比较,结果表明:比值域值法精度最高,达98.32%;将比值域值法提取1999年的冰川边界与1970年航测地形图勾绘的冰川边界进行叠加分析,得到整个流域29 a来的冰川变化信息.统计表明,流域冰川条数减少了0.6%,总面积萎缩了2.86%,总冰储量减少了3.10%,大多数冰川处于稳定状态.     

Lidar点云数据中建筑物的快速提取

Lidar技术可快速获取地表的高精度三维点云数据, 目前对此类数据的分类却是速度慢、精度低, 尤其是城市区域建筑物和树木靠得较近时更是难以准确提取建筑物.介绍了一种基于点云数据生成距离影像, 而后引入对比度纹理辅助的点云数据建筑物快速提取方法.结果证明, 该方法不需要其他辅助数据就能实现点云数据中建筑物的快速提取.      

基于三维激光扫描的空间地物建模

利用地面三维激光扫描仪获取的空间数据,进行了三维空间地物建模研究。以建筑物建模为例,首先从原始数据中分离提取建筑物,然后对得到的建筑物数据进行去噪处理,再通过整体匹配纠正并对原始测量数据进行重新采样和拼接配准,建立了由三角网构成的三维表面模型。结果表明,所构建的三维表面模型较好地表达了建筑物的几何特征,户外实验也验证了上述过程可以实现对建筑物快速三维建模。     

An object-based image analysis for building seismic vulnerability assessment using high-resolution remote sensing imagery

Building seismic vulnerability assessment plays an important role in formulating pre-disaster mitigation strategies for developing countries. The occurrence of high-resolution satellite sensors has greatly motivated it by providing a promising approach to obtain building information. However, this also brings a big challenge to the accurate building extraction and its coherent integration with the assessment model. The main objective of this paper is to investigate how to extract building attributes from high-resolution remote sensing imagery using the object-based image analysis (OBIA) method, so as to accurately and conveniently assess building seismic vulnerability by the combination of in situ field data. A general framework for the assessment of building seismic vulnerability is presented, including (1) the extraction of building information using OBIA, (2) building height estimation, and (3) the support vector machine (SVM)-based building seismic vulnerability assessment. Particularly, an integrated solution is proposed that merges the strengths of multiple spatial contextual relationships and some typical image object measures, under the unified framework to improve building information extraction at different scale levels as well as for different interest objects. With the aid of 35 building samples from two powerful earthquakes in China, the cloud-free WorldView-2 images and some building structure parameters from field survey were used to quantity the grades of building seismic vulnerability in Wuhan Optics Valley, China. The results show that all 48 buildings among the study area have been well detected with an overall accuracy of 80.67 % and the mean error of heights estimated from building shadow is less than 2 m. This indicates that the integrated analysis strategy based on OBIA is suitable for extracting the building information from high-resolution remote sensing imagery. Additionally, the assessment results using SVM show that the building seismic vulnerability is statistically significantly related to structure types and building heights. Both the proposed OBIA method and its integration strategy with SVM are easily implemented and provide readily interpretable assessment results for building seismic vulnerability. This reveals that the proposed method has a great potential to assist urban planners for making local disaster mitigation planning through the prioritization of intervention measures, such as the reinforcement of walls and the dismantlement of endangered houses.     

基于规则库的三维空间数据模型

三维空间对象的形式复杂多样,对象之间的空间关系尚未形成共识.三维空间数据模型的空间及非空间关系的表达更是难以统一.典型的三维空间数据模型包括面向实体型、面向关系型和混合型3种数据模型,但这些模型存在诸如拓扑操作困难、对象语义描述不完整、关系表达欠缺等一系列不足.通过分析、综合3种模型的优缺点,以顾及拓扑面向实体的三维矢量数据模型为基础,设计了基于规则库的三维空间数据模型.这是一个将关系与对象相统一的新型数据模型.通过对对象关系的分析研究,引入规则的概念,进而构建出规则库,提出对空间对象间关系和结构统一的,完整的表达和管理方式.结合地质、矿山等应用将该三维空间数据模型在多个城市的三维地质应用中进行成功验证.通过应用,说明该模型实现了空间对象的自身结构和对象之间关系的统一表达,具备自定义、可扩展的空间对象关系表达能力,能够适应复杂应用要求,具有良好的应用前景.      

1:25万赤布张错幅区域地质图空间数据库建设方法与意义

1:25万赤布张错幅区域地质图空间数据库建设是依据《数字地质图空间数据库标准》,将传统填图方法完成的1:25万区调图幅在当前空间数据库模型的典型代表地理数据库模型上建立的。该模型以研究实体为对象,把对象分为基本要素类、综合要素类和对象类,通过组成地质图基本要素类和对象类出发,处理和把握存储与组织的关系,采用关联、依赖、组合和继承来描述对象之间的关系规则来构成新的关联集合的技术,增强了数据库服务能力。     

Extensible, not relational: finding bodies in the landscape of electronic information with wireless body area networks

This article examines a medical biotechnology known as a wireless body area network (WBAN) as a way to discuss how electronic information infrastructure is spatially extending human bodies into physical landscapes. The term extensible body is introduced, framed by the object-oriented philosophy of Graham Harman. WBANs are sensors placed on or inside of the human body to measure, record, and transmit data about the biological processes of a medical patient. I argue that these body-data should be considered components of bodies themselves, not representations of them. Further, I argue that the geographical discourse on relationality should be less about object relations and more about object extensions. Harman’s explication of the “quadruple object,” and specifically his use of real and sensual objects makes this possible. This questions the spatial beginnings and ends of categorical objects such as bodies and information, the implications of which could have profound impacts on how policies are framed in sectors such as public health, environment, planning, and medicine. The notion of extensibility is crucial in theorizing how, and where, the Geoweb exists as a spatial-technical assemblage of objects and information. The case of WBANs shows that a theorization of the Geoweb must include the built infrastructure of data storage as a spatial extension of being human.     

Corner points localization in electronic topographic maps with deep neural networks

Digitized topographic maps normally have to go through the geometric calibration before practical utilization. Nowadays, the reference points for the calibration are still manually assigned. Corner points (graticule intersections) in a map are usually good candidates in favor of the reference points. This paper proposes an algorithm for automatically locating the corner points in the electronic topographic maps by detecting the specific rectangle objects in the map corners. It assigns the probabilities to each row and column in the region of interests (RoIs) to provide information regarding the location of the objects. In order to facilitate the object detection with high level visual features, the deep neural networks (DNNs) are employed in the proposed algorithm. For the object proposal, the sliding window scheme is adopted. The experimental results indicate that the proposed approach outperforms the conventional bounding-box regression method in both detection and localization accuracy. For the proposed algorithm, the average F1 score in the object detection is 0.91, which is 12% higher than the conventional model. The mean Euclidean distance between the predicted corner points and the ground-truth by the proposed algorithm is 2.22 pixels, 35.8% lower compared with the regression based model.     

面向对象的喀斯特地区土地利用遥感分类信息提取

传统的面向像元分类方法虽然对光谱差异较为明显的遥感影像信息提取具有较好的效果,但会不可避免地产生“椒盐现象”,同时对纹理和形状信息不能充分应用,造成了大量信息损失。为了提高喀斯特地区土地利用遥感信息提取的精度,本文采用面向对象的分类方法,对贵州省毕节地区开展了土地利用遥感信息自动提取研究。首先对该地区Landsat-5 TM影像进行多尺度分割,形成影像对象层,然后综合应用基于知识决策树分类和基于样本的最邻近分类等技术对喀斯特地区进行遥感解译。结果表明,面向对象分类技术能较好地对喀斯特地区土地利用信息进行提取,同时避免了“椒盐现象”的产生,经野外采集样点数据验证,一级类分类精度为91.7 %,二级类分类精度为89.4 %,表明该方法在贵州省毕节地区应用效果良好。      

Discrete modeling for natural objects

This paper presents a discrete technique specially designed for modeling the geometry and the properties of natural objects as those encountered in biology and geology. Contrary to classical Computer- Aided Design methods based on continuous (polynomial) functions, the proposed approach is based on a discretization of the objects close to the finite- element techniques used for solving differential equations. Each object is modeled as a set of interconnected nodes holding the geometry and the physical properties of the objects and the Discrete Smooth Interpolation method is used for fitting the geometry and the properties to complex data. Data are turned into linear constraints and some constraints related to typical information encountered in geology are presented.     

矿物蚀变区典型地物光谱特征初步研究——以内蒙古突泉县-扎鲁特旗成矿带为例

文章基于野外的实测光谱数据,对岩石、土壤和植被的光谱反射特征以及它们在统计空间的分布关系进行分析研究,总结中等植被覆盖的矿物蚀变区典型地物的光谱反射特征以及不同地物在光谱空间的分布规律,为矿物的遥感蚀变信息提取提供一定的科学依据,有利于改进蚀变信息提取的方法。