顾及拓扑联通性的互通式立交桥增量更新

由于互通式立交桥错综复杂的拓扑结构特点,使互通式立交桥更新时存在拓扑联通性维护困难的问题,针对该问题提出一种顾及拓扑联通性的互通式立交桥增量更新方法。该方法以21种互通式立交桥类型为基础,通过分析每种类型的拓扑结构特点,用计算匝道数和平面交点数组成的二元组值来识别这21种互通式立交桥;根据不同类型互通式立交桥需要维护的拓扑联通点和空间变化类型,设计66条互通式立交桥增量更新规则;最后在课题组1∶1万全球典型要素增量更新原型系统基础上,开发立交桥增量更新模块,实现互通式立交桥增量更新处理及拓扑联通关系维护的自动化。并以长沙市OSM道路网数据为试验数据,将其转换为1∶1万道路数据,验证本文方法的有效性。     

利用可变形部件模型检测遥感影像道路交叉口

为了解决高分辨率遥感影像道路交叉口位置检测与类型识别问题,提出了一种基于可变形部件模型的道路交叉口检测方法。首先,分析了道路交叉口在高分辨率遥感影像上的表征形式;然后,借鉴面向对象的思想,利用可变形部件模型,通过训练和学习其整体和部件组成的空间布局特征获取目标对象模型参数;最后,通过滑动窗口搜索匹配方法获取道路交叉口位置和其对应的类型。由仿真与实验结果可知,此算法不仅能够自动、准确地检测道路交叉口的几何位置,而且能够识别其几何形状类型,可有效提高道路网络拓扑结构构建效率。     

Improving urban road extraction in high-resolution images exploiting directional filtering, perceptual grouping, and simple topological concepts

In this letter, the problem of detecting urban road networks from high-resolution optical/synthetic aperture radar (SAR) images is addressed. To this end, this letter exploits a priori knowledge about road direction distribution in urban areas. In particular, this letter presents an adaptive filtering procedure able to capture the predominant directions of these roads and enhance the extraction results. After road element extraction, to both discard redundant segments and avoid gaps, a special perceptual grouping algorithm is devised, exploiting colinearity as well as proximity concepts. Finally, the road network topology is considered, checking for road intersections and regularizing the overall patterns using these focal points. The proposed procedure was tested on a pair of very high resolution images, one from an optical sensor and one from a SAR sensor. The experiments show an increase in both the completeness and the quality indexes for the extracted road network.     

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.     

Detection of clusters in traffic networks based on spatio‐temporal flow modeling

Spatio‐temporal clustering is a highly active research topic and a challenging issue in spatio‐temporal data mining. Many spatio‐temporal clustering methods have been designed for geo‐referenced time series. Under some special circumstances, such as monitoring traffic flow on roads, existing methods cannot handle the temporally dynamic and spatially heterogeneous correlations among road segments when detecting clusters. Therefore, this article develops a spatio‐temporal flow‐based approach to detect clusters in traffic networks. First, a spatio‐temporal flow process is modeled by combining network topology relations with real‐time traffic status. On this basis, spatio‐temporal neighborhoods are captured by considering traffic time‐series similarity in spatio‐temporal flows. Spatio‐temporal clusters are further formed by successive connection of spatio‐temporal neighbors. Experiments on traffic time series of central London's road network on both weekdays and weekends are performed to demonstrate the effectiveness and practicality of the proposed method.     

车辆轨迹数据提取道路交叉口特征的决策树模型

众源车辆轨迹数据隐含最新的道路分布信息,研究利用轨迹数据提取道路特征有益于基础路网数据的快速建库与更新。道路网由交叉口和连接交叉口的道路线构成,其中交叉口特征识别是整个道路网生成的关键。由于缺乏精细的交叉口识别模型,轨迹数据生成的道路网容易出现路口遗漏、结构失真等现象。针对这一问题,本文提出一种利用轨迹数据提取道路交叉口的方法。首先,分析车辆在交叉口与非交叉口区域移动轨迹几何形态及隐含动力学特征的变化情形;然后,利用决策树方法构建轨迹片段分类模型,并结合移动开窗式的轨迹线剖分模型建立交叉口区域变道轨迹片段提取方法;最后,依据Hausdorff距离对交叉口区域轨迹片段进行聚类,并提取中心线获得完整的道路交叉口结构。采用真实的车辆轨迹线作为测试数据,验证了本文提出方法的有效性。     

Length L-function for network-constrained point data

Network-constrained points are constrained by and distributed on road networks, for example, taxi pick-up and drop-off locations. The aggregation pattern (clustering) of network-constrained points (significantly denser than randomly distributed) along roads may indicate spatial anomalies. For example, detecting and quantifying the aggregation with the highest intensity (i.e., the number of taxi pick-up points per network length) can reveal high taxi demand. The network K-function and its derivative (incremental network K-function) have been utilized to identify point aggregations and measure aggregation scale, yet can only identify radius-based planar-scale results, thereby mis-estimating aggregation patterns owing to the network topology configuration heterogeneity. Specifically, complex road networks (e.g., intersections) may incur aggregations despite their low intensity. This study constructs the length L-function for network-constrained points, using its first derivative to quantify the true-to-life aggregation scale and the local function to extract aggregations. Synthetic and practical data experiments show innovative detection of aggregations at the length-based scale and with high intensity, providing a new approach to point pattern analysis of networks unaffected by topological complexity.     

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...     

Estimation of geometric route distance from its topological distance: application to narrow road networks in Tokyo

The structure of road networks has been investigated in accordance with the development of GIScience. By classifying road networks into wide and narrow ones, we can define the route as the path from the route’s origin (also called the root) on a wide road network to a narrow road segment which consists of the sequence of narrow road segments arranged by ascending order of the number of steps of adjacency to its root. The length of the route can be defined with the following geometric and topological terms: the route distance, measuring the length along the route and the depth, counting the number of road segments on the route. The depth plays the important role of being a substitute for the route distance in modelling road networks as a planar graph. Since road networks clearly exhibit irregular patterns and road segment lengths are non-uniform, it is considered appropriate to adopt a stochastic approach rather than a deterministic one to analyse the route distance. However, the relationship between the route distance and its depth has not been sufficiently investigated stochastically. Therefore, the research question is how can we estimate the route distance from its depth? Based on an empirical study in the Tokyo metropolitan region, it was found that (1) the statistical distribution of the route distance can be formulated as an Erlang distribution whose parameters are its depth and the inverse of the mean length of narrow road segments, and (2) this length is constant and close to 40 m. Therefore, we can estimate the route distance from only one parameter, the depth. Also, as a practical application, accessibility to the kth depth link in terms of firefighting was evaluated because the maximum length of the extension of fire hoses is approximately 200 m. It was found that (1) even if k?≤?5, the probability that the route distance to the kth depth link is equal to or longer than 200 m ranges from 0 to 0.45; and (2) if k?≥?8, the probability is approximately 1. These indicate the limitation of the deterministic approach because, on the basis of complete grid patterns (with intervals of 40 m between intersections), k?=?5 corresponds to a distance of 200 m from wide road networks and the route to the 5th depth link can be covered with fire hoses. Moreover, it was found that the connectivity of wide road networks is higher than that of narrow ones in terms of the smaller ratio of cul-de-sacs and the larger ratio of four-way intersections. These answers contribute substantially not only to constructing a science of cities that provides a simple model and specifies the most important parameter, but also to our understanding of the structure of narrow road networks within several hundred metres of wide road networks.     

An Integrated Multistage Framework for Automatic Road Extraction from High Resolution Satellite Imagery

Automated procedures to rapidly identify road networks from high-resolution satellite imagery are necessary for modern applications in GIS. In this paper, we propose an approach for automatic road extraction by integrating a set of appropriate modules in a unified framework, to solve this complex problem. The two main properties of roads used are: (1) spectral contrast with respect to background and (2) locally linear path. Support Vector Machine is used to discriminate between road and non-road segments. We propose a Dominant singular Measure (DSM) for the task of detecting linear (locally) road boundaries. This pair of information of road segments, obtained using Probabilistic SVM (PSVM) and DSM, is integrated using a modified Constraint Satisfaction Neural Network. Results of this integration are not satisfactory due to occlusion of roads, variation of road material, and curvilinear pattern. Suitable post-processing modules (segment linking and region part segmentation) have been designed to address these issues. The proposed non-model based approach is verified with extensive experimentations and performance compared with two state-of-the-art techniques and a GIS based tool, using multi-spectral satellite images. The proposed methodology is robust and shows superior performance (completeness and correctness are used as measures) in automating the process of road network extraction.     

User-centered road network traffic analysis with MobilityDB

Performance indicators of road networks are a long-lasting topic of research. Existing schemes assess network properties such as the average speed on road segments and the queuing time at intersections. The increasing availability of user trajectories, collected mainly using mobile phones with a variety of applications, creates opportunities for developing user-centered performance indicators. Performing such an analysis on big trajectory data sets remains a challenge for the existing data management systems, because they lack support for spatiotemporal trajectory data. This article presents an end-to-end solution, based on MobilityDB, a novel moving object database system that extends PostgreSQL with spatiotemporal data types and functions. A new class of indicators is proposed, focused on the users' experience. The indicators address the network design, the traffic flow, and the driving comfort of the motorists. Furthermore, these indicators are expressed as analytical MobilityDB queries over a big set of real vehicle trajectories.     

基于网眼密度的道路选取方法

道路数据中的网眼密度能反映局部区域的道路密集程度,通过确定目标尺度要求的密度阈值,比例尺缩小后能够标识出数据中需要取舍路段的网眼;循环剥离密度最大的网眼,利用反映路段重要性的参数及其优先级,渐进筛选出舍弃的路段,并完成与邻接网眼的合并;得到的选取结果保持了道路网在密度、拓扑、几何及语义方面的重要特征,从而提出一种新的道路选取方法。最后进行实验,验证该方法的有效性。     

多特征约束下的复杂交叉路口主辅路识别

主干道、辅路的准确识别对于实现复杂交叉路口的自动综合至关重要。传统方法多依赖于路段的笔直程度和弯曲程度描述路口的主干道和辅路，然而复杂交叉路口结构错综复杂、形态变化多样，仅依赖这两种特征进行主辅路识别的准确度有限，且部分形态相似的主辅路无法识别。为此，本文提出了一种多特征约束下的复杂交叉路口主辅路识别方法。首先提取复杂交叉路口的特征点，根据特征点对弧段进行打断，依据路段的笔直程度识别出平行弧段；然后依据道路延展性、角度、距离等特征识别平行簇获取复杂交叉路口中的主干道；最后通过紧凑度和距离关系识别匝道获取复杂交叉路口中的辅路。以南京OSM城市路网为例的试验表明，本文方法能够准确识别出复杂交叉路口的主干道和辅助路段，识别精度分别达到93.60%和89.43%。     

基于道路精简滤波原理的车辆导航系统地图匹配算法

针对交叉路口附近道路几何分布较为复杂的实际特点,提出基于道路精简滤波(RRF)原理的地图匹配算法。研究了基于D-S证据理论的多规则数据融合技术在二路段地图匹配中的应用。建立了最短欧氏距离和最小航向差两条判决规则。引入相关性模糊决策理论,将多路段匹配问题简化为二路段匹配问题,使D-S证据判决规则的概率分配函数能根据实际路网分布作适应性调整,提高了算法的鲁棒性。对实际跑车数据的仿真处理结果表明,应用该算法可以较好地解决城市交叉路口地图匹配问题。     

路网更新的轨迹-地图匹配方法

全面准确的路网信息作为智慧城市的重要基础之一,在城市规划、交通管理以及大众出行等方面具有重要意义和价值。然而,传统的基于测量的路网数据获取方式往往周期较长,不能及时反映最新的道路信息。近几年,随着定位技术在移动设备的广泛运用,国内外学者在研究路网信息获取时逐渐将视野转向移动对象的轨迹数据中所蕴含的道路信息。当前,基于移动位置信息的路网生成和更新方法多是直接面向全部轨迹数据施加道路提取算法,在处理大规模轨迹或者大范围道路时,计算量极大。为此,本文基于轨迹地图匹配技术,提出一种采用"检查→分析→提取→更新"过程的螺旋式路网数据更新策略。其主要思想是逐条输入轨迹,借助HMM地图匹配发现已有路网中的问题路段,进而从问题路段周边局部范围内的轨迹数据中提取并更新相关道路信息。该方法仅在局部范围内利用少量轨迹数据来修复路网,避免了对整个轨迹数据集进行计算,从而有效减少了计算量。基于OpenStreetMap的武汉市区路网数据以及武汉市出租车轨迹数据的试验表明,本文提出的路网更新方法不仅可行,而且灵活高效。     

A network distance and graph-partitioning-based clustering method for improving the accuracy of urban hotspot detection

Clustering is an important approach to identifying hotspots with broad applications, ranging from crime area analysis to transport prediction and urban planning. As an on-demand transport service, taxis play an important role in urban systems, and the pick-up and drop-off locations in taxi GPS trajectory data have been widely used to detect urban hotspots for various purposes. In this work, taxi drop-off events are represented as linear features in the context of the road network space. Based on such representation, instead of the most frequently used Euclidian distance, Jaccard distance is calculated to measure the similarity of road segments for cluster analysis, and further, a network distance and graph-partitioning-based clustering method is proposed for improving the accuracy of urban hotspot detection. A case study is conducted using taxi trajectory data collected from over 6500 taxis during one week, and the results indicate that the proposed method can identify urban hotspots more precisely.     

Automatic change detection for road networks from images based on GIS

Up to now, detailed strategies and algorithms of automatic change detection for road networks based on GIS have not been discussed. This paper discusses two different strategies of automatic change detection for images with low resolution and high resolution using old GIS data, and presents a buffer detection and tracing algorithm for detecting road from low-resolution images and a new profile tracing algorithm for detecting road from high-resolution images. For feature-level change detection (FL-CD), a so-called buffer detection algorithm is proposed to detect changes of features. Some ideas and algorithms of using GIS prior information and some context information such as substructures of road in high-resolution images to assist road detection and extraction are described in detail.     

Automatic Change Detection for Road Networks from Images Based on GIS

Up to now, detailed strategies and algorithms of automatic change detection for road networks based on GIS have not been discussed. This paper discusses two different strategies of automatic change detection for images with low resolution and high resolution using old GIS data, and presents a buffer detection and tracing algorithm for detecting road from low-resolution images and a new profile tracing algorithm for detecting road from high-resolution images. For feature-level change detection (FL-CD), a so-called buffer detection algorithm is proposed to detect changes of features. Some ideas and algorithms of using GIS prior information and some context information such as substructures of road in high-resolution images to assist road detection and extraction are described in detail.     

基于复杂网络的城市道路重要度评价及路网自动综合方法

利用复杂网络理论,构建城市复杂路网模型,基于该模型从道路的结构和功能特征角度,以连接度、介中心和接近度为度量指标定义道路重要度评价模型,并顾及路网的整体形态及路网的拓扑连通性,提出基于复杂网络理论的路网综合算法。为检验方法有效性,针对成都市道路网络进行实验分析。实验结果表明,该道路重要度评价模型较好地反映道路在整个路网结构和功能上的重要程度,复杂路网综合算法能较好地保持原始路网的整体形态结构特征。     

平行路段模式识别与简化初探

道路网模式中的平行路段作为一种局部模式,其识别与简化是地图综合研究的重要内容。本文在分析平行路段产生的原因和常见形态后,给出一种利于简化的平行路段分类方法,并提出基于平头缓冲区搜寻备选平行路段进而利用平行性测度判断路段是否平行的方法。在此基础上,针对3类平行路段分别提出对应的几何化简与连通关系简化方法。实验结果表明,该识别与简化方法能够对路网模式中的平行路段进行有效地综合,具有一定的实用价值,对进一步研究具有参考价值。