A Comparative Study of Various Supervised Learning Approaches to Selective Omission in a Road Network

Selective omission is necessary for road network generalisation. This study investigates the use of supervised learning approaches for selective omission in a road network. To be specific, at first, the properties to measure the importance of a road in the network are viewed as input attributes, and the decision of such a road is retained or not at a specific scale is viewed as an output class; then, a number of samples with known input and output are used to train a classifier; finally, this classifier can be used to determine whether other roads to be retained or not. In this study, a total of nine supervised learning approaches, i.e., ID3, C4·5, CRT, Random Tree, support vector machine (SVM), naive Bayes (NB), K-nearest neighbour (KNN), multilayer perception (MP) and binary logistic regression (BLR), are applied to three road networks for selective omission. The performances of these approaches are evaluated by both quantitative assessment and visual inception. Results show that: (1) in most cases, these approaches are effective and their classification accuracy is between 70% and 90%; (2) most of these approaches have similar performances, and they do not have any statistically significant difference; (3) but sometimes, ID3 and BLR performs significantly better than NB and SVM; NB and KNN perform significantly worse than MP, SVM and BLR.     

顾及结构和几何特征的道路自动选取方法

提出了一种顾及结构和几何特征的道路网自动选取方法。综合考虑道路的度中心性、集聚系数和路划的几何长度等道路选取影响因素,提出一种道路重要性评价方法。实验结果表明,本文方法能够很好地保持选取道路网的整体与局部结构、拓扑结构以及路网连通性。基于该方法,由大比例尺地图选取出的小比例尺地图与相应标准比例尺地图保持较高的一致性,表明该方法是稳定可靠的。     

利用道路网眼实现路网的增量式更新

获取现势性的交通道路数据是数字城市和智慧城市建设的基础,基于传统测绘的道路网更新方法存在一定局限性,而基于众源数据及行车轨迹数据更新道路网近年来则倍受关注。首先提出了一种新的道路变化增量更新方法,该方法先对历史道路网建立面拓扑结构,生成由道路网组成的最小闭合面域（道路网眼）;然后以道路网眼为基本控制单元,综合利用轨迹点上下文距离信息和隐马尔可夫模型（hidden Markov model,HMM）,提取失配轨迹点和失配轨迹段;最后采用缓冲区分析和最大密度法对失配轨迹提取骨架线,创建新增道路,增量更新历史道路网。实验结果表明,以道路网眼为控制单元,利用轨迹点上下文距离分析和HMM捕获失配轨迹点,可提高失配轨迹点的提取效率,改善道路网更新效果。该方法可用于大规模路网的增量式更新。     

How many samples are needed? An investigation of binary logistic regression for selective omission in a road network

ABSTRACT

Selective omission in a road network (or road selection) means to retain more important roads, and it is a necessary operator to transform a road network at a large scale to that at a smaller scale. This study discusses the use of the supervised learning approach to road selection, and investigates how many samples are needed for a good performance of road selection. More precisely, the binary logistic regression is employed and three road network data with different sizes and different target scales are involved for testing. The different percentages and numbers of strokes are randomly chosen for training a logistic regression model, which is further applied into the untrained strokes for validation. The performances of using the different sample sizes are mainly evaluated by an error rate estimate. Significance tests are also employed to investigate whether the use of different sample sizes shows statistically significant differences. The experimental results show that in most cases, the error rate estimate is around 0.1–0.2; more importantly, only a small number (e.g., 50–100) of training samples is needed, which indicates the usability of binary logistic regression for road selection.     

结合尺度空间的面向对象高分辨率影像城市道路提取

基于遥感影像的城市道路提取对于城市建设、规划和地图更新等有重要意义。针对高分辨率遥感影像城市道路网的复杂性,结合尺度空间思想提出一种面向对象的城市道路自动提取算法。在此基础上,使用Canny算子获取像元簇梯度图,并进行标记分水岭分割得到区域对象;建立城市道路与几何、光谱特征相关的道路规则,从分割结果中筛选出道路区域对象;使用形态学方法提取道路区域的骨架,并对骨架进行连接、光滑等后处理,最后输出道路网提取结果。实验结果表明,该方法用于复杂城市道路的高精度自动提取,对城市道路网更新有一定参考意义。     

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。     

改进全卷积网络方法的高分二号影像农村道路提取

针对目前利用高分遥感数据提取农村道路的研究与应用少,提取结果精准度不够的问题,提出了结合空洞卷积和ASPP（Atrous Spatial Pyramid Pooling）结构的改进全卷积农村道路提取网络模型DC-Net（Dilated Convolution Network）。该模型基于全卷积的编解码结构来提取道路深度特征信息,同时针对农村道路细长的特点,在解编码层之间加入了以空洞卷积为基础的ASPP（Atrous Spatial Pyramid Pooling）结构来提取道路的多尺度特征信息,在不牺牲特征空间分辨率的同时扩大了特征感受野FOV（Field-of-View）,从而提高细窄农村道路的识别率。以长株潭城市群郊区部分区域为试验对象,以高分二号国产卫星遥感影像为实验数据,将本文提出的方法与经典的几种全卷积网络方法进行实验结果对比分析。实验结果表明：（1）本文所提出的道路提取模型DC-Net在农村道路的提取上具有可行性,整体提取平均精度达到98.72%,具有较高的提取精度;（2）对比几种经典的全卷积网络模型在农村道路提取上的效果,DC-Net在农村道路提取的精度和连结性、以及树木和阴影的遮挡方面,均表现出了较好的提取结果;（3）本文提出的改进全卷积网络道路提取模型能够有效地提取高分辨率遥感影像中农村道路的特征信息,总体提取效果较好,为提高基于国产高分影像的农村道路提取精度提供了一种新的思路和方法。     

两种道路选取策略的比较研究

道路选取是根据比例尺的要求,在道路网中保留相对重要道路、舍弃相对次要道路的地图综合操作。从概念层和操作层对两种不同的道路选取策略进行了比较。一种是删除后更新策略,即删除一条道路后更新其他道路的重要度;另一种是删除后不更新策略,即删除一条道路后不更新其他道路的重要度。以常用的stroke重要度排序法为道路选取方法,运用长度、连通度、接近度和中介度的加权来描述道路的重要度,采用相似性、误删率、漏删率等定量指标以及定性的目视判别评价选取结果。以深圳市1∶1万道路网和1∶5万道路网作为研究数据进行了实验。理论上删除后更新策略优于删除后不更新策略,然而实证表明删除后不更新策略在常用定量评价指标上优于删除后更新策略,在定性评价方面则各有优劣。     

径向基函数神经网络的路网自动匹配算法

针对VGI数据中检测更新的问题,该文提出基于径向基函数的神经网络自动匹配算法。通过选取路段的距离、方向、形状和长度4个空间特征的相似度作为衡量路段是否匹配的指标。考虑到4个空间特征指标对匹配的影响力不同,在RBF(radial basis function)神经网络中的隐含层对基函数引入粒度拉伸因子,使径向对称的RBF顾及各向异性。同时对输出层在线性加权求和函数的基础上引入sigmoid函数,使计算结果(路段的匹配度值)归一化。该算法对数据质量较差的VGI路网具有很好的匹配能力,与BP神经网络相比,RBF神经网络在地图匹配中具有更好的匹配效率。     

小比例尺道路网眼约束下的多尺度道路网自动匹配

针对道路网多尺度匹配的问题,提出了一种在小比例尺数据道路网眼约束下的多尺度道路匹配方法。首先,构建两幅不同比例尺数据的道路网眼;其次,在小比例尺道路网眼的约束下,提取出大比例尺道路中由若干道路网眼构成的复合网眼,并完成与小比例尺道路网眼具有多对一和一对一关系的网眼匹配;然后,实现不同比例尺道路网眼的多对多匹配;最后,由复合网眼与小比例尺道路网眼的匹配关系转化为多比例尺道路网眼边界道路之间的匹配和内部道路之间的匹配,完成整个道路网的匹配。试验结果证明,本方法能较好地实现多尺度道路网的匹配。     

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。     

Self-organised clustering for road extraction in classified imagery

The extraction of road networks from digital imagery is a fundamental image analysis operation. Common problems encountered in automated road extraction include high sensitivity to typical scene clutter in high-resolution imagery, and inefficiency to meaningfully exploit multispectral imagery (MSI). With a ground sample distance (GSD) of less than 2 m per pixel, roads can be broadly described as elongated regions. We propose an approach of elongated region-based analysis for 2D road extraction from high-resolution imagery, which is suitable for MSI, and is insensitive to conventional edge definition. A self-organising road map (SORM) algorithm is presented, inspired from a specialised variation of Kohonen's self-organising map (SOM) neural network algorithm. A spectrally classified high-resolution image is assumed to be the input for our analysis. Our approach proceeds by performing spatial cluster analysis as a mid-level processing technique. This allows us to improve tolerance to road clutter in high-resolution images, and to minimise the effect on road extraction of common classification errors. This approach is designed in consideration of the emerging trend towards high-resolution multispectral sensors. Preliminary results demonstrate robust road extraction ability due to the non-local approach, when presented with noisy input.     

顾及双线道路特征的变化信息提取方法

在城市双线道路数据更新的需求下,通过分析已有要素匹配方法,提出了一种顾及双线道路特征的单、双线道路匹配方法,用于提取城市双线道路增量更新中的变化信息。为保证双线道路的整体性,将双线道路多边形作为匹配对象,通过分析旧单线道路与多边形的方向、长度以及位置关系设计了单、双线道路匹配综合指标计算模型;然后,根据匹配综合指标确定单、双线道路匹配关系并提取变化信息。实验结果表明,该方法能够较好地满足双线道路更新中变化信息提取的要求,具有一定的实用性。     

Selection of Streets from a Network Using Self-Organizing Maps

We propose a novel approach to selection of important streets from a network, based on the technique of a self‐organizing map (SOM), an artificial neural network algorithm for data clustering and visualization. Using the SOM training process, the approach derives a set of neurons by considering multiple attributes including topological, geometric and semantic properties of streets. The set of neurons constitutes a SOM, with which each neuron corresponds to a set of streets with similar properties. Our approach creates an exploratory linkage between the SOM and a street network, thus providing a visual tool to cluster streets interactively. The approach is validated with a case study applied to the street network in Munich, Germany.     

Mapping Rice Paddies in Complex Landscapes with Convolutional Neural Networks and Phenological Metrics

ABSTRACT

Rice mapping with remote sensing imagery provides an alternative means for estimating crop-yield and performing land management due to the large geographical coverage and low cost of remotely sensed data. Rice mapping in Southern China, however, is very difficult as rice paddies are patchy and fragmented, reflecting the undulating and varied topography. In addition, abandoned lands widely exist in Southern China due to rapid urbanization. Abandoned lands are easily confused with paddy fields, thereby degrading the classification accuracy of rice paddies in such complex landscape regions. To address this problem, the present study proposes an innovative method for rice mapping through combining a convolutional neural network (CNN) model and a decision tree (DT) method with phenological metrics. First, a pre-trained LeNet-5 Model using the UC Merced Dataset was developed to classify the cropland class from other land cover types, i.e. built-up, rivers, forests. Then, paddy rice field was separated from abandoned land in the cropland class using a DT model with phenological metrics derived from the time-series data of the normalized difference vegetation index (NDVI). The accuracy of the proposed classification methods was compared with three other classification techniques, namely, back propagation neural network (BPNN), original CNN, pre-trained CNN applied to HJ-1 A/B charge-coupled device (CCD) images of Zhuzhou City, Hunan Province, China. Results suggest that the proposed method achieved an overall accuracy of 93.56%, much higher than those of other methods. This indicates that the proposed method can efficiently accommodate the challenges of rice mapping in regions with complex landscapes.     

应用PSInSAR技术分析上海道路网沉降时空特性

城市道路网的持续稳定性监测不仅可以避免重大事故带来的人身财产损失,也有利于经济社会的可持续发展。针对道路网长距离、大跨度的实时监测需求,将永久散射体雷达干涉测量（persistent scatterer synthetic aperture radar interferometry,PSInSAR）技术引入城市道路网的形变监测和预警,处理了上海26景时间序列TerraSAR-X卫星数据,对道路网的沉降进行时空分析。空间上,首先阐述道路网整体的沉降格局,然后探讨局部路段的沉降细节及其驱动力;时间上,分析温度变化对路面沉降时间序列变化的影响,并对实验结果进行精度验证。结果表明,上海道路网沉降主要分布在浦东区,与路网密度相关,新区城市化发展建设已成为道路网主要的沉降原因;沥青路面的沉降时间序列与温度变化存在时间相关性,沉降结果与水准数据基本一致。     

基于改进Snake模型的道路网空间冲突处理

在对Snake模型研究分析的基础上,结合地图制图的需求,从3个方面对Snake模型进行改进：首先建立Snake模型中参数与道路曲线形态特征的关系,以更好地保持移位前后道路形态的相似性;其次控制Snake模型中外力的传播范围,以尽量保持要素位置的准确性;最后,通过道路交叉点的权重属性控制,保证移位后各交叉点的连通性以及道路的整体拓扑关系不发生变化。在此基础上,提出道路网移位整体思路,并采用改进的Snake模型对其进行移位,解决空间冲突。     

A New Neuro-Fuzzy Approach for Post-earthquake Road Damage Assessment Using GA and SVM Classification from QuickBird Satellite Images

Tracking damaged roads and damage level assessment after earthquake is vital in finding optimal paths and conducting rescue missions. In this study, a new approach is proposed for the semi-automatic detection and assessment of damaged roads in urban areas using pre-event vector map and both pre and post-earthquake QuickBird images. In this research, damage is defined as debris of damaged buildings, presence of parked cars and collapsed limbs of trees on the road surface. Various texture and spectral features are considered and a genetic algorithm is used to find the optimal features. Subsequently, a support vector machine classification is applied to the optimal features to detect damages. The proposed method was tested on QuickBird pan-sharpened images from the Bam earthquake and the results indicate that an overall accuracy of 93% and a kappa coefficient of 0.91 were achieved for the damage detection step. Finally, an appropriate fuzzy inference system (FIS) and also an “Adaptive Neuro-Fuzzy Inference System” are proposed for the road damage level assessment. These results show that ANFIS has achieved overall accuracy of 94% in comparison with 88% of FIS. The obtained results indicate the efficiency and accuracy of the Neuro-Fuzzy systems for road damage assessment.     

Semi Automatic Road Extraction by Fusion of High Resolution Optical and Radar Images

Two new methods for fusion of high-resolution optical and radar satellite images have been proposed to extract roads in high quality in this paper. Two fusion methods, including neural network and knowledge-based fusion are introduced. The first proposed method consists of two stages: (i) separate road detection using each dataset and (ii) fusion of the results obtained using a neural network. In this method, the neural networks are separately applied on high-resolution IKONOS and TerraSAR-X images for road detection, using a variety of texture parameters. The outputs of two neural networks, as well as the spectral features of optical image, are used in a third neural network as inputs. The second method is a knowledge-based fusion using thresholds of narrow roads and vegetation gray levels. First roads are extracted from each source separately. The outputs are then compared and advantages and disadvantages of each data source are investigated . The results obtained from accuracy assessment show the efficiency of the proposed methods. Furthermore, the comparison of the results showed the superiority of the first algorithm.     

一种基于平行系数的双线主干道识别方法

城市主干道路的识别和提取是路网综合的关键步骤,而双线道路则是大比例尺地图数据中道路综合的难点。针对城市双线主干道识别问题,基于Gestalt视觉准则构建候选双线主干道线对的约束条件,提出了一种基于平行系数的双线主干道识别方法。首先对道路网数据进行拓扑处理,然后借助道路匹配思想,结合Hausdorff（HD）距离匹配方法识别出可能构成双线主干道的候选线对。再对候选线对进行平行系数计算,当平行系数满足阈值条件时,就判定该线对是构成双线主干道的弧段。最后根据构成双线主干道路段间的空间关系,将已识别的弧段连接成整条道路。实验证明,选取典型样本方法正确设置阈值后,该方法能有效地提取道路网中的双线主干道。