遥感图像土地覆盖分类中多源特征数据选择研究

多源特征数据可以提高遥感图像的分类精度,选择合适的特征数据十分重要。利用基尼指数对多尺度纹理信息、主成分变换前三分量、地形数据等特征进行选择,选出最佳特征子集。利用支持向量机、神经网络分类法、最大似然法分别对全部特征数据和最佳特征子集结合多光谱数据进行分类。实验结果表明:基尼指数可以有效地对多源特征数据进行选择,特征选择可以提高分类器效率,提高分类精度。     

地形模型数控雕刻技术研究与实现

针对传统的地形模型加工方法引起的地貌表达失真和加工效率低等问题,该文提出了基于数字高程模型的地形模型数控雕刻技术。采用地形图形特征化处理地貌特征失真和微地貌丢失问题,较好地表达了区域地貌特征;依据地貌特征优化雕刻参数匹配求解地形模型的精细雕刻和加工效率之间矛盾,实现了地形模型的精确表达和快速加工。生产实验结果表明,地形模型数控雕刻技术不仅解决了地貌特征表达问题,提升了地形模型的表达力,还实现了地形模型的快速成型。研究结果对地形模型的开发和应用具有重要的参考价值。     

多特征融合的高分辨率影像建筑物变化检测

为充分发挥遥感影像中各特征的优势,提高遥感影像建筑物变化检测精度,基于面向对象的分析方法,提出了一种基于模糊集合的证据理论特征信息融合的变化检测方法。首先,在影像分割的基础上,利用变化矢量分析法分别计算前后时相对应对象的光谱、纹理特征差异及形态学建筑物指数差异;然后,以Sigmoid函数作为隶属度函数,计算对象属于变化类和非变化类的隶属度并以之构建证据理论所需的基本概率分配函数;最后,利用证据理论对多种特征进行融合并通过规则判定得到建筑物变化区域。利用不同地区影像的试验结果表明,该方法能够有效融合影像的多种特征,提高建筑物变化检测的精度。     

融合像素—多尺度区域特征的高分辨率遥感影像分类算法

针对基于像素多特征的高分辨率遥感影像分类算法的"胡椒盐"现象和面向对象影像分析方法的"平滑地物细节"现象,提出了一种融合像素特征和多尺度区域特征的高分辨率遥感影像分类算法。(1)首先采用均值漂移算法对原始影像进行初始过分割,然后对初始过分割结果进行多尺度的区域合并,形成多尺度分割结果。根据多尺度区域合并RMI指数变化和分割尺度对分类精度的影响,确定最优分割尺度。(2)融合光谱特征、像元形状指数PSI(Pixel Shape Index)、初始尺度和最优尺度区域特征,并对多类型特征进行归一化,最后结合支持向量机(SVM)进行分类。实验结果表明该算法既能有效减少基于像素多特征的高分辨率遥感影像分类算法的"胡椒盐"现象,又能保持地物对象的完整性和地物细节信息,提高易混淆类别(如阴影和街道,裸地和草地)的分类精度。     

融合多尺度特征注意力的遥感影像变化检测方法EI北大核心CSCD

深度学习技术已经成为遥感影像变化检测研究的主流方法,现有的基于深度学习的变化检测方法主要是获取单一尺度的变化特征,而在现实场景中,变化区域的尺度具有多样性。为此,本文提出了融合多尺度特征注意力的遥感影像变化检测方法,通过关注多尺度融合策略来解决变化检测存在的多尺度问题。首先,利用特征金字塔网络自身的多尺度特性,使网络学习到不同尺度的变化特征,为了提升网络感受野和利用全局特征信息,在特征提取网络末端引入扩张卷积空间金字塔模块;然后,在不同变化特征融合时,使用变化特征融合模块来控制信息传播以减少特征融合时的差异性;最后,使用门控机制,将不同尺度预测的变化特征图进行加权求和,最终产生具有高精度的变化特征图。本文方法不仅能获取多尺度变化特征,还能利用全局信息和精确的空间细节来提升预测特征图的空间精度。对比试验表明,本文方法在变化检测基准数据集CDD和LEVIR-CD上取得了较好的结果,召回率分别提高了6.58%和5.26%。     

基于多尺度融合特征卷积神经网络的遥感图像飞机目标检测

飞机检测在遥感图像解译中具有重要的研究意义。针对现有目标检测算法对于复杂场景区域或飞机密集区域的小尺度飞机目标检测精度较低的问题,本文提出了一种端到端的多尺度特征融合飞机目标检测框架MultDet。该方法基于SSD多尺度检测框架,采用轻量级基础网络提取多尺度特征信息;然后设计反卷积特征融合模块,通过跳跃连接将高层语义特征与低层细节特征进行特征融合,得到结构层次丰富的多尺度融合特征;最后设计了一系列不同纵横比的候选框以适应多尺度飞机目标检测。本文在光学遥感图像数据集UCAS-AOD上进行数据分析试验,结果表明,MultDet512在飞机数据集上取得了94.8%的平均检测精度(average precision,AP),在Titan Xp GPU上达到0.0500s/img的检测速度。本文所提飞机目标检测算法在包含多种复杂场景的遥感图像中,能够实现多尺度飞机目标的高精度稳健检测。     

Validating the use of object-based image analysis to map commonly recognized landform features in the United States

ABSTRACT

The U.S. Geological Survey (USGS) National Geospatial Program (NGP) seeks to i) create semantically accessible terrain features from the pixel-based 3D Elevation Program (3DEP) data, and ii) enhance the usability of the USGS Geographic Names Information System (GNIS) by associating boundaries with GNIS features whose spatial representation is currently limited to 2D point locations. Geographic object-based image analysis (GEOBIA) was determined to be a promising method to approach both goals. An existing GEOBIA workflow was modified and the resulting segmented objects and terrain categories tested for a strategically chosen physiographic province in the mid-western US, the Ozark Plateaus. The chi-squared test of independence confirmed that there is significant overall spatial association between terrain categories of the GEOBIA and GNIS feature classes. Contingency table analysis also suggests strong category-specific associations between select GNIS and GEOBIA classes. However, 3D visual analysis revealed that GEOBIA objects resembled segmented regions more than they did individual landform objects, with their boundaries often failing to correspond to match what people would likely perceive as landforms. Still, objects derived through GEOBIA can provide initial baseline landscape divisions that can improve the efficiency of more specialized feature extraction methods.     

面向对象的泰安市高分辨率影像住宅建筑物提取

基于eCognition Developer平台,以泰安市QuickBird影像为数据,采用面向对象多尺度分割、最邻近和隶属度分类,充分利用高分辨率QuickBird影像具有的丰富光谱、形状、纹理和结构等地物信息,对实验区进行分类并提取住宅建筑物信息。实验表明,与传统逐像元分类法相比,面向对象分类法有效地避免了分割区域的离散破碎,地类信息的提取更加完整、精确、高效。     

多尺度表达中线状要素的综合不确定性评价模型

在考虑节点化简的基础上建立了节点数据不确定性评价模型,基于曲线光滑模型建立了线元模型不确定性评价模型,在此基础上,根据不确定性传播律构建了由数据不确定性和模型不确定性合成的线状要素多尺度表达不确定性的综合评价模型。实验表明,综合不确定性指标值作为线状要素多尺度表达不确定性的量化指标是有效的。可将其用于计算线元不确定带的宽度,解决线状要素多尺度表达不确定性空间分析和推理问题;并用于线状要素多尺度表达的质量评价与控制。     

顾及“保真性”原则的双向滚动球变换DDM多尺度表达算法

在分析符合"安全性"要求的数字水深模型(DDM)正向滚动球变换应用局限的基础上,根据高保真DDM多尺度表达评价标准中对水深值准确性、严密有序性及地形信息等级嵌套性的要求,从顾及"保真性"原则的DDM多尺度表达需要出发,提出一种基于双向滚动球变换的DDM多尺度表达算法。分析了海底地貌特征点在DDM双向滚动球变换过程中的变化趋势,根据DDM正向滚动球变换的尺度依赖特性,计算出了一定尺度下海底地貌的横向分布范围与纵向分布高度,建立了DDM多尺度表达中细部(骨架)地貌的判定准则。通过保留给定尺度下DDM中的骨架地貌,使海底地形的整体变化趋势得到了保持,满足了DDM多尺度表达对水深值准确性的要求;论证了DDM单值曲面等距离面变换的水深序同构特性,通过对给定尺度下的细部地貌进行DDM双向滚动球变换的等距离面提取,使海底地形的局部起伏形态得到了保持,满足了DDM多尺度表达对水深值严密有序性的要求;从满足DDM多尺度表达对地形信息等级嵌套性的要求出发,分析了DDM双向滚动球变换中尺度因子与地形信息等级单元逻辑包含关系的不相关性,论证了任意尺度因子条件下具有的相应等级地形信息范围的一致性。试验结果表明该算法克服了DDM正向滚动球变换存在的无法保留负向骨架地貌和保持海底局部地形起伏形态等不足,可有效保留DDM中骨架地貌并综合细部地貌,满足顾及"保真性"原则的DDM多尺度表达要求。     

地形特征提取的一种简易算法

地形特征作为基本地理要素,从DEM数据中提取其隐含的地形结构信息是非常重要的。本方法采用距离倒数加权法建立格网DEM,提出一种直接比较高程值来提取地形特征的简易算法,并利用差分算法计算坡度和坡向,通过V isual C++软件平台,编程实现格网DEM地形特征的自动提取,进行三维立体显示。该算法易于编程实现,数据结构简单,程序运行效率高,提取结果与真实地形基本拟合。     

结合UPSCALING技术与对象多特征的土地利用覆盖信息提取研究

应用SPOT融合数据,以北京密云地区为例,提出了整合Upscaling技术与对象多特征方法的新思路,通过基于半变异函数的 空间变异特征分析,建立了面向对象多特征与多分辨率数据集的多尺度分类决策树,并对自动分类效率进行了初步探讨。     

A History and Analysis of Mapping Urban Expansion in the Kathmandu Valley,Nepal

Abstract

There have been numerous efforts over many years to map or delineate urban locations and features in the Kathmandu Valley of Nepal. This study acquired 27 land useland cover maps for the Valley or the urban portions of the Valley. Those maps vary greatly in their mapping parameters. The objectives of this study were to first conduct a cartographic comparison of the differences in the creation and content of the maps and then do an analysis of the urban changes in the Valley based upon the maps. The maps for the Valley have differed in their source materials, the amount of field work involved, scale and minimum mapping units, classifications used, definitions of classes and coordinate systems. Source materials have included various scales and formats of aerial photography and different satellite systems. The most difficult issue in comparing the maps is the varied classification systems and definitions. The same feature will be classified differently from map to map. This is particularly an issue for institutional features such as temples, palaces, educational facilities, open public space and governmental sites. Definitions of residential areas are also not consistent. Even with the differences in mapping parameters, considerable useful information can be obtained by comparing these maps. These include a simply documentation of the urban extent and the generally resulting loss in agricultural lands. There was an increase in urban extent from 22 to 83km² between 1955 and 2000. Urban expansion has also changed from occurring on the upland river terraces or tars to the floodplains. Finally, while not directly documented in these maps, the tremendous pace of urban growth has resulted in multiple infrastructure and environmental challenges.     

Generalization of DEM for terrain analysis using a compound method

This paper reports an investigation into the generalization of a grid-based digital elevation model (DEM) for the purpose of terrain analysis. The focus is on the method of restructuring the grid-based surface elevation data to form a triangulated irregular network (TIN) that is optimized to keep the important terrain features and slope morphology with the minimum number of sample points. The critical points of the terrain surface are extracted from the DEM based on their significance, measured not only by their local relief, but also by their importance in identifying inherent geomorphological and drainage features in the DEM. A compound method is proposed by integrating the traditional point-additive and feature-point methods to construct a drainage-constrained TIN. The outcome is then compared with those derived from other selected methods including filtering, point-additive or feature-point algorithms. The results show that the compound approach is capable of taking advantage of both point-additive and feature-point algorithms to maximally keep the terrain features and to maintain RMSE at an acceptable level, while reducing the elevation data points by over 99%. The analytical result also shows that the proposed method outperforms the compared methods with better control in retaining drainage features at the same level of RMSE.     

Land productivity assessment and mapping through integration of satellite and terrain slope data

Evaluation and mapping of spatial variations of land productivity is very important for effective landuse planning. The present study was undertaken in watershed of the Song river (Dehra Dun district, U.P.), for assessing and mapping land productivity using modified Storie Index following integrated approach. This approach utilizes soilscape information (derived from digital IRS-IA LISS-II data), soil characteristics (field observed and laboratory analysed) and terrain slope information (obtained from Survey of India topographical maps). The approach consists of preparation of Storie Index productivity rating factors such as: A (soil profile character), B (soil texture), X (soil physical and fertility conditions), and C (land slope), and computerised integration of these maps to generate land productivity map. The results indicate that in the watershed 30.6%, 19.6%, 12.2%, 11.8% and 18.8% areas have been found to be under good, fair, poor, very poor and not suitable, land productivity classes, respectively.     

Detection of gullies in roughly textured terrain using airborne laser scanning data

Airborne laser scanning data contain information about surface features, some of which are of subtle form. These features are usually embedded within the terrain, and rarely form distinct shape-transition to their surroundings. While some efforts have been made in extracting linear elements from laser scanning data, attention was mostly turned to dominant elements that are very clear and distinct. We present in this paper a detection model for gullies of various dimensions using airborne laser scanning data. Gullies are regarded as one of the main landform-reshaping agents, having a pejorative effect on the environment and on regional development. They are commonly observed along receding lakes as a common response to water-level drop. The paper demonstrates how a multi-scale approach enables the extraction of various gully forms, from well developed to subtle. It then proposes an optimization driven model for handling fragmentation in the detection. Results show that using the proposed model, gully networks can be reconstructed and ∼30 cm deep features can be identified and separated from their surroundings using moderate point density data.     

The derivation of skeleton lines for terrain features

The geometric and physical analysis methods are conventional methods for the derivation of skeleton lines in the fields of cartography,digital photogrammetry,and related areas.this paper proposes a stepwise approach that uses the physical analysis method in the first stage and the geometric analysis method in the subsequent stage.The physical analysis method analyses the terrain globally to obtain a rough set of skeleton lines for a terrain surface.The rough skeleton lines help to structure the ordering of feature points by the geometric analysis method.     

The derivation of skeleton lines for terrain features

The geometric and physical analysis methods are conventional methods for the derivation of skeleton lines in the fields of cartography, digital photogrammetry, and related areas. This paper proposes a stepwise approach that uses the physical analysis method in the first stage and the geometric analysis method in the subsequent stage. The physical analysis method analyses the terrain globally to obtain a rough set of skeleton lines for a terrain surface. The rough skeleton lines help to structure the ordering of feature points by the geometric analysis method.     

高光谱影像的引导滤波多尺度特征提取

为了解决高光谱遥感影像分类中单一尺度特征无法有效表达地物类间差异和区分地物边界的不足,提高影像分类精度和改善分类目视解译效果,提出了采用引导滤波提取多尺度的空间特征的方法。首先,利用主成分分析对高光谱影像进行降维,移除噪声并突出主要特征;然后,将第1主成分作为引导影像,将包含信息量最多的若干主成分分别作为输入影像,应用依次增加的滤波半径分别进行引导滤波处理提取多个尺度的特征,获得影像不同尺度的结构信息;最后,将多尺度特征输入分类器中进行影像监督分类。采用仿真数据和帕维亚大学(Pavia University)、帕维亚城区(Pavia Centre)等3幅高光谱实验数据,提取了基于引导滤波的多尺度特征、多尺度形态特征和多尺度纹理特征,输入到支持向量机、随机森林和K近邻分类器中,进行了实验。实验结果表明:采用支持向量机分类Pavia University数据,相对于采用多尺度形态特征的分类结果,引导滤波特征的总体精度提高了6.5%;Pavia Centre和Salinas两幅影像最高分类精度均由引导滤波特征实现,分别达到98.51%和98.39%。实验证实基于引导滤波提取的多尺度特征能有效地描述地物结构,进而获得更高的分类精度和改善目视解译效果。