一种适应局部密度变化的空间聚类方法

研究一种适应空间局部密度变化的空间聚类算法(简称ADBSC).在该算法中,首先提出一种新的空间局部密度度量方法,即k-空间近邻最大距离,而为了表达空间局部密度变化特征,引入距离变化率概念,用于度量邻近目标间空间局部密度变化情况.然后将所有空间邻近的距离变化率小于给定变化率阈值的空间目标标记为局部密度相等,再将空间邻近的局部密度相等的空间目标聚为一类,得到空间聚类结果.并给出ADBSC算法的详细描述和计算过程.最后,通过模拟实验和实际算例,对提出的方法进行验证.结果表明,该算法能够自动适应空间位置的局部密度变化,适应不同形态的空间簇,而且比DBSCAN算法更实用.     

重力梯度特征向量和多尺度分析法在密度异常深度探测中的应用

相较于传统的重力测量手段,重力梯度测量能够以更高的灵敏度和分辨率反映出地下密度异常体的结构特征。随着科学技术的不断发展,航空及卫星重力梯度测量系统已经投入使用,并实现了大范围高精度的重力梯度测量。因此,现阶段的主要挑战在于对越来越多的重力梯度数据进行分析、处理和解释。本文根据重力梯度全张量主特征值对应的特征向量,对密度异常体的深度探测进行了研究。由于不同埋深的密度异常体具有不同的波长反映,利用多尺度分析法可以分解出不同频段重力梯度张量,从而增强对更大埋深密度异常体的探测分析能力。通过对模型和实测重力梯度数据的分析解算,结果表明,重力梯度的特征向量和多尺度分析法能够有效地确定密度异常体的深度信息,并且对干扰场源和随机噪声也具有一定的抗干扰能力。     

A Multi‐Objective,Multi‐Criteria Approach to Improve Situational Awareness in Emergency Evacuation Routing Using Mobile Phone Data

Emergency services personnel face risks and uncertainty as they respond to natural and anthropogenic events. Their primary goal is to minimize the loss of life and property, especially in neighborhoods with high population densities, where response time is of great importance. In recent years, mobile phones have become a primary communication device during emergencies. The portability of cell phones and ease of information storage and dissemination has enabled effective implementation of cell phones by first responders and one of the most viable means of communication with the population. Using cellular location data during evacuation planning and response also provides increased awareness to emergency personnel. This article introduces a multi‐objective, multi‐criteria approach to determining optimum evacuation routes in an urban setting. The first objective is to calculate evacuation routes for individual cell phone locations, minimizing the time it would take for a sample population to evacuate to designated safe zones based on both distance and congestion criteria. The second objective is to maximize coverage of individual cell phone locations, using the criteria of underlying geographic features, distance and congestion. In summary, this article presents a network‐based methodology for providing additional analytic support to emergency services personnel for evacuation planning.     

融合图论与密度思想的混合空间聚类方法

提出了一种融合图论与密度思想的空间聚类方法——HGDSC。该方法首先借助附加约束的Delau-nay三角网来建立空间实体之间的邻接关系,然后对基于密度的聚类方法进行改进,顾及空间邻近与非空间属性相似性进行聚类。特别地,该方法只需要一个输入参数。模拟数据和实际数据验证表明,HGDSC方法能够发现任意形状和密度变化的空间簇,并且可以很好地识别噪声点。     

A Multi‐Grid Method of High Accuracy Surface Modeling and Its Validation

A method of high accuracy surface modeling (HASM) has been constructed to find a solution for error problems that had long troubled surface modeling in geographical information systems (GIS). It is found that when a preconditioned conjugate gradient (PCG) algorithm is used to solve the large sparse linear system, which HASM can be transferred into, HASM performs best in terms of simulation compared with all other algorithms. But its computing speed is not fast enough for all applications. A multi‐grid method is introduced into HASM to try to shorten its computing time. Both numerical and real‐world tests demonstrate that there is a range of stop error (SE). The multi‐grid method of HASM (HASM‐MG) greatly increases computing speed when SEs are within this range, compared with the PCG algorithm of HASM (HASM‐PCG). HASM‐MG is suitable for applications with a need for less accuracy and a shorter computing time. HASM‐PCG is appropriate for issues needing higher accuracy. HASM‐MG performs better than HASM‐PCG in flat areas, while HASM‐PCG does better in complex terrainm in terms of accuracy and computing time.     

Automated Target Detection and Discrimination Using Constrained Kurtosis Maximization

Exploiting hyperspectral imagery without prior information is a challenge. Under this circumstance, unsupervised target detection becomes an anomaly detection problem. We propose an effective algorithm for target detection and discrimination based on the normalized fourth central moment named kurtosis, which can measure the flatness of a distribution. Small targets in hyperspectral imagery contribute to the tail of a distribution, thus making it heavier. The Gaussian distribution is completely determined by the first two order statistics and has zero kurtosis. Consequently, kurtosis measures the deviation of a distribution from the background and is suitable for anomaly/target detection. When imposing appropriate inequality constraints on the kurtosis to be maximized, the resulting constrained kurtosis maximization (CKM) algorithm will be able to quickly detect small targets with several projections. Compared to the widely used unconstrained kurtosis maximization algorithm, i.e., fast independent component analysis, the CKM algorithm may detect small targets with fewer projections and yield a slightly higher detection rate.     

A Theoretical Framework for Hyperspectral Anomaly Detection Using Spectral and Spatial A Priori Information

This letter presents a new theoretical approach for anomaly detection using a priori information about targets. This a priori knowledge deals with the general spectral behavior and the spatial distribution of targets. In this letter, we consider subpixel and isolated targets that are spectrally anomalous in one region of the spectrum but not in another. This method is totally different from matched filters that suffer from a relative sensitivity to low errors in the target spectral signature. We incorporate the spectral a priori knowledge in a new detection distance, and we propose a Bayesian approach with a Markovian regularization to suppress the potential targets that do not respect the spatial a priori. The interest of the method is illustrated on simulated data consisting in realistic anomalies that are superimposed on a real HyMap hyperspectral image.     

Multi‐Scale Qualitative Location: A Topology‐Based Model

Qualitative locations describe spatial objects by relating the spatial objects to a frame of reference (e.g. a regional partition in this study) with qualitative relations. Existing models only formalize spatial objects, frames of reference, and their relations at one scale, thus limiting their applicability in representing location changes of spatial objects across scales. A topology‐based, multi‐scale qualitative location model is proposed to represent the associations of multiple representations of the same objects with respect to the frames of reference at different levels. Multi‐scale regional partitions are first presented to be the frames of reference at multiple levels of scale. Multi‐scale locations are then formalized to relate multiple representations of the same objects to the multiple frames of reference by topological relations. Since spatial objects, frames of reference, and topological relations in qualitative locations are scale dependent, scale transformation approaches are presented to derive possible coarse locations from detailed locations by incorporating polygon merging, polygon‐to‐line and polygon‐to‐point operators.     

多尺度点云噪声检测的密度分析法

当前机载激光雷达数据和影像匹配得到的点云是密集点云数据的两类主要来源,但都不可避免存在着噪声点。本文提出一种新的点云去噪算法,可适用于这两类数据中所包含的噪声点的去除。算法主要包括两步:第1步利用多尺度的密度算法去除孤立噪声和小的簇状噪声;第2步利用三角网约束将第1步中误检测为噪声的点重新归为正常点。针对真实数据进行了剔噪试验,结果表明本文提出的基于密度分析的多尺度噪声检测算法对孤立噪声和簇状噪声都有较为效,且对于质量较差的影像匹配点云的检测也能有效处理。本文算法检测率达到97%以上。     

多特征融合的建筑物点云检测方法

当前各种影像数据以及Li DAR数据获取能力不断增强,仅利用一种数据进行建筑物的检测,其结果往往并不理想。本文对Li DAR点云数据的特征和影像的相关特征进行了分析,融合这些特征,利用支持向量机的方法对建筑物点云进行检测。实验结果表明,综合利用具有不同特征的点云和影像数据的方法比单纯使用点云数据进行建筑物的检测能够取得更好的效果。     

利用CART分类树分类检测交通拥堵点

交通拥堵检测是城市交通管理工作的重点和难点之一,现有的拥堵检测以路段为单位,不利于拥堵时空演变规律信息的提取,且检测内容大多只涉及拥堵程度,缺少对拥堵类型的识别。基于CART（classification and regression tree）分类树算法,提出一种以路段点为检测单元的拥堵点分类检测方法,该方法可根据路段平均行驶速度实时检测拥堵点及其类型。首先,将路段等距离划分后映射为路段点,根据时空维路况异常规则和异常模式,以路段点为单元分析了4种拥堵类型的时空演变模式;其次,在路段路况检测的基础上,提取路段点路况时空序列,根据不同类型的拥堵模式对路况时空序列进行分类标记;然后,选取4种速度指标作为样本属性集合,按照属性集合提取各路段点在各时段的速度,以此作为决策树学习的数据集;最后,基于CART分类树算法,采用交叉验证的方式训练出最优模型,使其达到最佳的泛化能力。与支持向量机（support vector machine, SVM）分类模型进行比较,实验结果表明,该方法在分类检测交通拥堵点时具有较高的正确率和召回率,且分类检测时效性较好。     

顾及局域信息的核化正交子空间投影目标探测方法

提出了一种基于局域信息的核化正交子空间投影的目标探测方法(KLOSP).模拟数据实验证明,KLOSP方法比其他子空间目标探测方法具有更优的接受者操纵特征曲线;真实影像数据实验证明,该方法比传统子空间目标探测方法具有更大的目标与背景的可分度,能够准确地对高光谱影像数据进行目标探测.     

Street‐level Spatial Interpolation Using Network‐based IDW and Ordinary Kriging

This study proposes network‐based spatial interpolation methods to help predict unknown spatial values along networks more accurately. It expands on two of the commonly used spatial interpolation methods, IDW (inverse distance weighting) and OK (ordinary kriging), and applies them to analyze spatial data observed on a network. The study first provides the methodological framework, and it then examines the validity of the proposed methods by cross‐validating elevations from two contrasting patterns of street network and comparing the MSEs (Mean Squared Errors) of the predicted values measured with the two proposed network‐based methods and their conventional counterparts. The study suggests that both network‐based IDW and network‐based OK are generally more accurate than their existing counterparts, with network‐based OK constantly outperforming the other methods. The network‐based methods also turn out to be more sensitive to the edge effect, and their performance improves after edge correction. Furthermore, the MSEs of standard OK and network‐based OK improve as more sample locations are used, whereas those of standard IDW and network‐based IDW remain stable regardless of the number of sample locations. The two network‐based methods use a similar set of sample locations, and their performance is inherently affected by the difference in their weight distribution among sample locations.     

一种波段融合的分类变化检测方法

针对图像分类后变化检测两次单独分类造成的误差累积问题,在结合图像波段融合原理的基础上,将变化检测问题转化为影像分类问题,提出一种利用图像融合构造差异图的方法.所提出的方法同分类后变化检测法相比,只进行一次分类就能实现变化检测,在一定程度上避免了分类误差造成的误差累积问题.结果表明,利用该方法能够初步实现变化检测,且该方...     

利用高分辨率光学遥感图像检测震害损毁建筑物

地震发生后,利用高分辨率遥感图像进行建筑物损毁检测,有利于快速评估灾害损失。在分析损毁建筑物梯度分布的基础上,提出了一种利用梯度局部空间统计检测震害损毁建筑物的方法。首先用Prewitt算子提取图像梯度信息;然后对梯度图像进行局部空间统计,统计各建筑物屋顶内部梯度的空间相关性,得到初步损毁检测结果;最后,在先验知识的指导下进行极小值分析和阴影检测,进一步修正建筑物损毁检测结果。分别以玉树地震后的Quickbird卫星遥感图像和盈江地震后的光学航空图像为例进行实验,结果表明,利用梯度局部空间统计检测震害损毁建筑物的方法效果优于传统损毁检测方法,总体精度达到80%以上,能够有效检测损毁建筑物。     

一种新的融合空间信息的半监督变化监测方法

基于改进的半监督FCM算法和马尔科夫随机场,提出了一种新的融合空间信息的半监督变化监测方法。首先将两幅遥感图像相减得到差值图像,并通过第4波段的差值给出了一种新的样本标记方法;然后,通过标记样本对差值图像利用半监督FCM算法进行聚类;最后,为了提高监测精度和去除聚类噪音点,利用像元点之间的空间邻接关系和马尔科夫随机场,通过更新后的隶属度矩阵得到了监测结果。为了验证本文方法的有效性,选取了两组TM遥感图像,监测了森林的变化。试验结果表明,改进的半监督FCM算法可以减少监测的漏检率,马尔科夫随机场方法可以很好地去除聚类过程中形成的噪声点,减少监测的虚检率。     

顾及密度对比的多层次聚类点群选取方法

在语义信息缺乏的情况下进行点群选取是制图综合的难点之一。提出了一种新的通过多层次聚类进行点群选取的方法。首先,针对k-means聚类算法的不足,利用改进的密度峰值聚类算法实现点群自动聚类,主要表现为用基尼系数确定最优截断距离及用局部密度和相对距离的关系自动确定聚类中心。其次,提出一种顾及密度对比的选取策略,通过点群多层次聚类,将点群划分成不同等级的簇,确定不同等级的聚类中心,建立点群的层次树结构;依据方根定律计算的选取数量,按照各级别簇的点数比例,自上而下逐层分配待选取点数,确定选取对象,实现点群的自动选取和多尺度表达。对不同分布模式的点群进行实验,验证了该方法的普适性和有效性。     

Tree Detection in Urban Regions Using Aerial Lidar and Image Data

In this letter, we present an approach to detecting trees in registered aerial image and range data obtained via lidar. The motivation for this problem comes from automated 3-D city modeling, in which such data are used to generate the models. Representing the trees in these models is problematic because the data are usually too sparsely sampled in tree regions to create an accurate 3-D model of the trees. Furthermore, including the tree data points interferes with the polygonization step of the building roof top models. Therefore, it is advantageous to detect and remove points that represent trees in both lidar and aerial imagery. In this letter, we propose a two-step method for tree detection consisting of segmentation followed by classification. The segmentation is done using a simple region-growing algorithm using weighted features from aerial image and lidar, such as height, texture map, height variation, and normal vector estimates. The weights for the features are determined using a learning method on random walks. The classification is done using the weighted support vector machines, allowing us to control the misclassification rate. The overall problem is formulated as a binary detection problem, and the results presented as receiver operating characteristic curves are shown to validate our approach     

朝鲜人口统计数据空间化模拟及影响因子分析

朝鲜人口统计数据空间化是解决朝鲜统计数据与自然要素数据融合分析的重要途径。基于朝鲜市郡级人口普查数据,将GIS空间分析技术与统计学方法相结合,分析了朝鲜人口密度与空间因子的关系,采用多元回归的方法建立了朝鲜人口密度空间化模型,在GIS平台中实现了朝鲜人口密度的空间格网化模拟,并利用地理探测器对影响朝鲜人口密度空间分布因素的决定力进行了有效探测。结果表明,多元回归模型拟合精度达到0.769,生成的栅格人口密度数据与朝鲜三级行政区人口统计数据保持一致。同时,影响该地区人口密度的因子依次为道路网密度、居民点密度、居民地指数、海拔、坡度和耕地指数。     

A Back‐Propagation Neural Network‐Based Approach for Multi‐Represented Feature Matching in Update Propagation

Spatial data infrastructures, which are characterized by multi‐represented datasets, are prevalent throughout the world. The multi‐represented datasets contain different representations for identical real‐world entities. Therefore, update propagation is useful and required for maintaining multi‐represented datasets. The key to update propagation is the detection of identical features in different datasets that represent corresponding real‐world entities and the detection of changes in updated datasets. Using polygon features of settlements as examples, this article addresses these key problems and proposes an approach for multi‐represented feature matching based on spatial similarity and a back‐propagation neural network (BPNN). Although this approach only utilizes the measures of distance, area, direction and length, it dynamically and objectively determines the weight of each measure through intelligent learning; in contrast, traditional approaches determine weight using expertise. Therefore, the weight may be variable in different data contexts but not for different levels of expertise. This approach can be applied not only to one‐to‐one matching but also to one‐to‐many and many‐to‐many matching. Experiments are designed using two different approaches and four datasets that encompass an area in China. The goals are to demonstrate the weight differences in different data contexts and to measure the performance of the BPNN‐based feature matching approach.