基于C4.5算法的道路网网格模式识别

道路网模式的识别对于地图综合、数据匹配和空间分析具有重要意义。网格模式是道路网中的典型模式之一。本文提出一种基于C4.5算法的网格模式识别方法。该方法以道路网中的网眼多边形为基本单元,根据上下文关系将其标识为属于网格模式和不属于网格模式两类。首先采用形状参量和关系参量描述网眼多边形,然后,基于决策树C4.5算法分别对5维参量和3维参量构造分类器,运用10折交叉验证获得具有说服力的结果,其Kappa值分别为0.63和0.66,正确率分别为81.7％和82.9％,置信度90％的置信区间分别为[0.785, 0.846]和[0.797, 0.857]。在新数据上进行了识别效果的验证,结果表明该分类器可用于网格模式的识别。研究试图将传统模式识别和数据挖掘的理论方法应用于空间问题的解答中。     

利用路段连接图识别道路网中的格网模式

提出一种基于路段连接图的格网模式识别方法.该方法以路段连接对作为研究的基本单元,以节点路段为点,路段的连接为边用路段连接图表达道路网.将在道路网中识别格网转化为在路段连接图中搜索格网回路.提出了描述路段连接对几何与连接关系的5个参量,用于筛选图中符合格网特点的节点和边.设计了图搜索的约束条件,使用广度优先遍历搜索连接关...     

运用图论进行道路网网格模式提取

提出了一种基于图论的网格模式提取方法。该方法根据道路之间的关系生成关系图,运用交、联、提取连通分量和极大完全子图等图论算子完成模式的提取。实验结果表明,该方法能有效地进行网格模式的提取。     

运用自组织映射识别街道网中的网格模式

提出了一种运用自组织映射识别网格模式的方法。首先,计算街道网中网眼的参数,这些参数是质心、面积、矩形度、延展度、是否含有平行边、边数、一阶邻居数和矩形度平均值;然后,将网眼作为自组织映射的向量进行训练,利用U-matrix可视化方法挖掘聚类得出结果。实验结果表明,该方法能有效地从不规则街道网中识别出网格模式。     

Towards an Automated Comparison of OpenStreetMap with Authoritative Road Datasets

OpenStreetMap (OSM) is an extraordinarily large and diverse spatial database of the world. Road networks are amongst the most frequently occurring spatial content within the OSM database. These road network representations are usable in many applications. However the quality of these representations can vary between locations. Comparing OSM road networks with authoritative road datasets for a given area or region is an important task in assessing OSM's fitness for use for applications like routing and navigation. Such comparisons can be technically challenging and no software implementation exists which facilitates them easily and automatically. In this article we develop and propose a flexible methodology for comparing the geometry of OSM road network data with other road datasets. Quantitative measures for the completeness and spatial accuracy of OSM are computed, including the compatibility of OSM road data with other map databases. Our methodology provides users with significant flexibility in how they can adjust the parameterization to suit their needs. This software implementation is exclusively built on open source software and a significant degree of automation is provided for these comparisons. This software can subsequently be extended and adapted for comparison between OSM and other external road datasets.     

网络空间向量剖分法识别城市路网网格模式

将道路网络空间视为嵌在2D空间中的独立子空间,利用形态单一的线性单元剖分图结构的边,实现网络空间的栅格化;提取网格模式的典型特征,包括几何和拓扑特征,以栅格单元邻域为目标计算特征值,构建特征向量描述栅格单元,实现对象空间到特征空间的映射,构建空间向量场;基于支持向量机（support vector machine,SVM）实现网格模式分类;结合格式塔原则完善实验结果。将此方法应用于深圳市路网数据,实验结果表明能有效地识别网格模式。     

联合卷积神经网络与集成学习的遥感影像场景分类

针对人工设计的中、低层特征难以实现复杂场景影像的高精度分类以及卷积神经网络依赖大量训练数据等问题，结合迁移学习与集成学习，提出了一种联合卷积神经网络与集成学习的遥感影像场景分类算法。首先基于迁移学习的思想，利用在自然影像数据集上训练好的多个深层卷积神经网络模型作为特征提取器，提取图像多个高度抽象的语义特征；然后构建由Logistic回归和支持向量机组成的Stacking集成模型，对同一图像的多个特征分别训练Logistic模型，将预测概率结果融合构建概率特征；最后利用支持向量机对概率特征训练和预测，得到场景影像的分类结果。利用UCMerced_LandUse和NWPU-RESISC 45两种不同规模的遥感影像数据集进行试验，即使在只有10%的数据作为训练样本情况下，本文方法能够分别达到90.74%和87.21%的分类精度。     

On the degree correlation of urban road networks

Recent advances in network science and the development of volunteered geographic information (VGI) have created new research opportunities in the topological analysis of road networks. The degree correlation of road networks is rarely studied. This study applied four measures, including the average degree of nearest neighbor, correlation profile, Newman's assortativity coefficient, and Litvak–Hofstad's assortativity coefficient, to measure the degree correlations of road networks represented as dual graphs of strokes, axial lines, and named roads. After investigating 100 road networks worldwide obtained from OpenStreetMap, it has been found that road networks are mostly disassortative or uncorrelated in stroke and named road representations, but assortative when represented as axial lines. Inconsistency in different measures persists regardless of method of representation; therefore, qualitative dichotomy or trichotomy is insufficient to describe the actual connection pattern in road networks. A taxonomy of road network assortativity is proposed. Two of the proposed disassortative types are associated with the absence of a grid pattern and are less robust than the typical disassortative type.     

基于改进霍夫变换的环形交叉口识别方法

空间分布模式识别对地图综合、地图匹配等具有重要意义。环形交叉口是道路微观环形模式的典型代表。本文以改进的霍夫变换检测矢量圆环为基础,提出一种环形交叉口的几何识别方法。该方法将环形交叉口的识别分为环路识别和支路识别两部分,首先通过圆环识别、均匀度优化及相似度优化3个子过程识别环路,然后再通过连通性判别、支路分类和组合支路补充3个步骤提取支路。选取英国某区域道路网数据进行测试,结果表明,本文方法能够有效识别道路网中的环形交叉口,且召回率和准确率均高于对比方法。     

顾及路网结构保持的城镇居民地自动综合

以往居民地自动综合的研究多集中于建筑物的多边形化简,较少考虑到其与街区、道路网的联系。提出了顾及路网结构保持的城镇居民地自动综合模型,此模型包含道路选取和街区内部结构概括两方面。前者基于网眼密度并结合路划功能选取道路数据,用于街区合并;后者则主要涉及建筑物多边形化简,通过改进矩形差分组合方法,在原有面积阈值的基础上添加距离阈值,并提供新的分层化简思路。以1:1万地图数据到1:5万比例尺的自动综合实验验证了本文算法的可行性和有效性。     

Mobile user identification based on road networks and multiple distance measures

Mobile user identification aims at matching different mobile devices of the same user using trajectory data, which has attracted extensive research in recent years. Most of the previous work extracted trajectory features based on regular grids, which will lead to incorrect feature representation due to lack of geographic information. Besides, most trajectory similarity models only considered one single distance measure to calculate the similarity between users, which ignore the connection between different distance measures and may lead to some false matches. In light of this, we present a novel user identification method based on road networks and multiple distance measures in this article. The proposed method segments a city map into several grids and road segments based on road networks. Then it extracts location and road information of trajectories to jointly construct user features. Multiple distance measures are fused by a discriminant model to improve the effect of user identification. Experiments on real GPS trajectory datasets show that our proposed method outperforms related similarity measure methods and is stable for mobile user identification. Meanwhile, our method can also achieve good identification results even on sparse trajectory datasets.     

A Pattern‐Based Approach for Matching Nodes in Heterogeneous Urban Road Networks

This article presents an approach to hierarchical matching of nodes in heterogeneous road networks in the same urban area. Heterogeneous road networks not only exist at different levels of detail (LoD), but also have different coordinate systems, leading to difficulties in matching and integrating them. To overcome these difficulties, a pattern‐based method was implemented. Based on the authors' previous work on detecting patterns of divided highways, complex road junctions, and strokes to eliminate the LoD effect of road networks, the proposed method extracts the local networks around each node in a road network and uses them as the matching units for the nodes. Second, the degree of shape similarity between the matching units is measured using a Minimum Road Edit Distance based on a transformation. Finally, the proposed method hierarchically matches the nodes in a road network using the Minimum Road Edit Distance and eliminates false matching nodes using M‐estimators. An experiment involving matching heterogeneous road networks with different LoDs and coordinate systems was carried out to verify the validity of the proposed method. The method achieves good and effective matching regardless of differences in LoDs and road‐network coordinate systems.     

一种适用于多类别遥感图象分类的新方法——复合神经网络分类方法

该文提出一种由多层神经网络与自组织神经网络相结合进行类别遥感图象分类的复合神经网络分类方法。第１步半训练样本按其统计特征分成若干组，用不同级别的训练样本分别训练ＢＰ网络。第２步将这些训练好的ＢＰ网络并联构成有监督分类器，对遥感图象进行有监督分类。第３步用ＢＰ网络的分类结果对Ｋｏｈｏｎｅｎ网络进行自组织训练，用训练好的Ｋｏｈｏｎｅｎ网络构造无监督分类器，对遥感图象进行细分。通过对ＳＰＯＴ遥感图象的分     

保持城市道路格网模式的街区合并混合整数规划模型

基于最优化建模理论提出一种保持城市道路格网模式的街区合并混合整数规划模型。首先定义道路格网模式保持的目标函数,集成了紧密性、骨干性、排列一致性和合并方向性四个评价指标;然后构建四个合并约束条件,包括合并尺度、路划删除、联动合并和连通性保持,来保证合并过程正确有效且满足目标尺度需求,;最后利用已识别的主干道和格网模式对道路网进行分区,在保持道路网的骨架和格网结构模式的基础上对每个分区内的道路街区独立建立最优化合并模型。本文采用数学最优化规划程序CPLEX对模型进行求解。。实验使用ATKIS 1:25000数据,将其简化至1:100000并与已有数据作比较。结果表明,通过本方法简化的道路网能够保持道路网中整体和局部的模式特征。     

基于地理格网的复杂路线车辆通行时间估算方法

车辆通行时间隐含了特定时隙的交通状况，准确地计算该时间在交通监测和路径规划中具有重要意义。现有研究通常利用车辆历史轨迹估算一定距离内选定路径的通行时间，然而当路径距离较长时，限于很难找到完整穿越指定路径的历史轨迹而无法对其通行时间进行准确估计；此外，海量历史轨迹在估计路径通行时间时会产生巨大的数据管理和计算压力。因此，本文引入地理格网，首先构建统一的时空索引，将路网及其历史轨迹分别划分为一系列落在地理格网单元（Cell）中的路段模式及轨迹段；然后利用一系列频繁共享轨迹在Cell中的停留时间计算车辆在当前路段模式的通行时间；最后通过一组历史时段相似路径模式的通行时间估算较长路线的车辆通行时间。通过对北京市10 000辆出租车一周的轨迹数据进行试验，验证了本文方法在处理海量历史轨迹数据上的有效性，以及在估算较长路径上车辆通行时间的优越性。     

网络约束下局部空间同位模式的扫描统计方法

空间同位模式挖掘旨在发现空间数据库中频繁发生在邻近位置的地理事件。由于空间异质性,地理事件在不同区域邻近出现的频繁程度亦存在差异,进而形成局部同位模式。现有局部同位模式挖掘方法多基于欧氏空间的平面假设,难以客观揭示网络空间（如城市道路）内地理事件间的局部同位规律,因此基于空间扫描统计思想,提出了一种网络约束下的局部同位模式挖掘方法。首先,发展了网络约束下的路径扩展方法,识别可能存在局部网络空间同位模式的候选路径;其次,基于网络约束下的二元泊松分布构建显著性检验的零模型,判别候选路径中局部网络空间同位模式的有效性。通过模拟实验与北京市出租车供需模式分析,发现该方法比现有方法得到的结果更精细、更客观,能够有效地挖掘网络约束下的局部同位模式。     

结合多分类器的遥感数据专题分类方法研究

采用标准的多分类器结合方法进行遥感图像的分类研究。首先介绍了标准的多分类器结合的算法,然后以Landsat-TM多光谱遥感数据的土地覆被分类为例,分别给出了抽象级上相同训练特征的多分类器结合、抽象级上不同训练特征的多分类器结合和测量级上的多分类器结合进行土地覆被分类的方法,并进行了实例研究。参与分类器结合的单个分类器包括最大似然分类器,最小距离分类器,马氏距离分类器,K-NN分类器,多层感知器神经网络分类器。分类器的分类精度用总体精度、用户精度、生产者精度、kappa系数和条件kappa系数评价。结果表明,每一种多分类器结合的分类方法都能够比较显著地提高总体分类精度。文章最后对不同多分类器结合方式的优缺点进行了分析。     

基于有向属性关系图的典型道路交叉口结构识别方法

提出采用有向属性关系图描述道路交叉口结构,形成典型道路交叉口结构模板库.通过将道路网矢量表示转化成有向属性关系图表示,采用图匹配技术识别道路网中的典型交叉口.实现有关算法,通过试验验证该方法的有效性,并分析其局限性和适用范围.该方法可在基于结构的交叉口简化过程中用于典型交叉口结构识别.     

Entropy-based fuzzy classification parameter optimization using uncertainty variation across spatial resolution

In the past researchers have suggested hard classification approaches for pure pixel remote sensing data and to handle mixed pixels soft classification approaches have been studied for land cover mapping. In this research work, while selecting fuzzy c-means (FCM) as a base soft classifier entropy parameter has been added. For this research work Resourcesat-1 (IRS-P6) datasets from AWIFS, LISSIII and LISS-IV sensors of same date have been used. AWIFS and LISS-III datasets have been used for classification and LISS-III and LISS-IV data were used for reference data generation, respectively. Soft classified outputs from entropy based FCM classifiers for AWIFS and LISS-III datasets have been evaluated using sub-pixel confusion uncertainty matrix (SCM). It has been observed that output from FCM classifier has higher classification accuracy with higher uncertainty but entropy-based classifier with optimum value of regularizing parameter generates classified output with minimum uncertainty.     

VGI数据与地形图数据的自动融合研究

随着科学技术的不断发展，志愿者地理信息（volunteered geographic information，VGI）已经成为地理空间数据中最为重要的来源之一。为了充分利用志愿者地理信息，需要进行VGI与传统地形图数据的匹配与融合。开发了一种全新的数据自动匹配与融合算法，其目的是将ATKIS道路网数据（由德国联邦测绘局所采集的官方数据）与AOSD数据（由大量志愿者携带定位仪器进行户外徒步或骑行所获取的轨迹数据）匹配并融合起来，从而丰富传统地理信息数据的内容，并实现数据的增值。考虑到ATKIS数据与AOSD数据在空间表达上的差异很大，所开发的算法包括了道路要素的智能化分割、道路要素匹配、道路网数据融合以及融合后道路网内部要素间的匹配运算与数据集成等4个过程。大量实地数据的测试结果表明，该算法具有匹配成功率高、准确率高、运算速度快等优点。