提出了一种顾及操作性、稳定 性、精度和速度的从航空影象半自动提取线状地物的策略和算法 .在人工依次输入的每两个初始点之间 ,提取连续的抛物线 .该方法先通过二值模板快速相关和优化计算得到剔除了错误匹配后的初始抛物线参数 ,然后以其为初值 ,基于整体最小二乘模板匹配 ,解求参数的精确值 ,以获得更高的定位精度 .通过自适应的模板克服了线特征的对比度和线宽度的变化对定位带来的影响 .实验结果表明 ,该算法有较强的抗干扰能力和较高的精度 ,有较好的实用价值

In this paper, we propose a novel semi-automatic ribbon road extraction schemewhich combines angular tex-ture signature and profile matching. The angular texture signature was proposed byHaverkamp in 2002 for extracting straight road structure from IKONOS satellite mi agery. In thismethod, a rectangular template region rotates around a spe-cific pointwith certain angle intervals, and computes texture signature ofallpoints in this template region ateach position of rotation. The basic texture signature is variance and the entropy also to be tested in this paper. A profilemeans that in the centerline points, perpendicular to the direction of the road, we painta straight line segment, and extractgray values of various points along the line segment. And the straight line segmentshould be longer than the roadwidth. Profilematc-hing calculates the least square values between profile line model and the profile in the predicted points. To a certain extent, we offsetthe profile in the predicted pointofand calculate valuesofatthe leastsquare each offsetposition, we be-lieve the corresponding offsetwith theminmi um value should be possible pointofroad centerline, therefore, the final road centerline can be determined through predicted points and the offset least square values.In the scheme, user inputs the initial position, direction,and width of the road firstly. The initial road centerline points are predicted based on angular texture signature,and road center trajectorymodel is created using parameters of parabola. Themultiple linear regressionmethod is used for acquiring the road trajectory parameters, andwe utilize these parameters and the initial centerline points coordinates to compute the initialmean of the curvature. Thenwemake use of themethod of curvature change to verify the points in trajectory. By comparing the value and the given threshold,we re got following conclusion: if it exceeds the lmi it,the verification fails, a profilematching algorithm willbe used to re-predict and decide the position of centerpoints again;if the value doesn texceed the lmi it, the verification succeeds, we believe the centerline points predicted in angular texture signature is the finalposition. In the algorithm, themanual intervention is necessary especially for complex situation. After the verification, we can achieve the final centerline points and add them to the trajectory. If these two algorithms both fai,l we could decide the final centerline point completelymanually.In thispaper, we mi plementthe abovementioned scheme and build a prototype system usingVisualC++, and veri-fy the extraction resultofribbon roadswith appropriatewidth inQuickBird and IKONOS mi agery. In the expermi ent1, the road hasuniform texture, and the contrasttobackground isobvious, butno obviousobstructionson the road. In this situa-tion, the scheme extracts thewhole road automaticallywithout anymanual intervention. In the expermi ent2, the ribbon road extraction from IKONOS is generally successful and need a fewmanual intervention. In the expermi ent3,a rather complex situationwith several roads in an digitalaerial mi age, we extract themain roads automatically and some junctions of the roads needs semi-automatic extraction, but the final result is satisfactory. We also utilize expermi ents to compare our schemewith traditionalprofilematching semi-automatic extraction algorithm and Snakes algorithm. After these experi-mental verification, itproves this semi-automatic ribbon road extraction scheme can achieve good results.

提出了一种基于角度纹理特征及剖面匹配相结合的高分辨率遥感影像带状道路半自动提取方法.该方法由用户输入道路起点、初始方向及宽度,使用角度纹理特征模型预测初始的道路中线点,以抛物线方程参数构建道路中线轨迹参数模型.使用计算曲率变化的方法验证道路轨迹点,对验证失败的中线点位使用剖面匹配算法进行重新预测并确定,最终提取出该道路中线轨迹.本文使用Visual C 构建了原型系统,对QuickBird及IKONOS影像中具有一定宽度的带状道路进行了提取试验,并与经典的基于剖面匹配的半自动道路提取算法和基于Snakes的半自动道路提取算法进行了对比试验.经试验验证,本算法取得了较为理想的结果.

摘要 致力于在复杂环境下能对多种道路进行检测，提出了一种先验知识库与自适应区域增长相融合的道路检测方法，通过少量的道路样本采集，建立样本库，训练挖掘出道路知识模型，并结合区域增长方法对分割的实时道路影像进行道路区域增长。实验结果表明，该方法适用于多种不同环境道路的提取，鲁棒性强。

提出一种利用纹理与几何特征的高分辨率遥感影像道路提取方法.首先分析高分辨率遥感影像的纹理特征,提出基于纹理特征的聚类方法,将影像大致分为道路区域 和非道路区域,然后选取适当的几何特征指数,剔除道路区域中含有的非道路像素,得到初步道路信息.最后通过数学形态学处理,去除初步道路信息中由于车道 线、树木影响而产生的孔洞,最后得到完整的道路信息.实验结果表明,与传统方法相比,该方法能够有效地从高分辨率遥感影像中提取道路.

According to the characteristics of urban road in high-resolution remote sensing image, this paper presents an approach to extract the urban road from high-resolution remote sensing images based on Hough transform and path morphology. The method uses Hough transform to detect the direction and the length of main roads, and to construct the adjacency graph, according to each direction adjacency graph determine the path. These paths can be regarded as narrow, the elongation but not completely straight structure elements. Experimental results show that it not only can detect straight road information easily, but also can detect the wide crooked road information and the curvature of smaller slender road information.

针对高分辨率遥感影像上城区道路的特点，提出一种基于Hough变换和路径形态学的高分辨率遥感影像城区道路提取方法。用Hough变换检测主要道路的方向及长度，建立邻接图，根据邻接图确定路径的方向和长度，将这些确定的路径看作狭长但并非完全笔直的结构元素。实验结果表明，该方法不仅能够检测出直线道路信息，还能检测出宽的弯曲的道路及细长的曲率比较小的道路信息。

根据城市道路在高分辨率遥感影像中的形态特性,提出一种基于形态重建的提取方法。试验结果表明,该方法能有效地从高分辨率遥感影像中提取出城市道路网。

针对卫星图像中道路的基本特征以及道路信息提取的难点,提出了一种基于区域生长型分水岭算法的卫星图像主干道路提取方法.该方法首先运用高通滤波器对原始图像进行去噪和平滑,然后采用区域生长型分水岭算法提取道路信息,最后用目标面积特征将误提的小斑点去除.实验结果表明,该方法性能良好,可以取得很好的效果.

There are still many problems needed to resolve about extracting road from remote sensing image, although a lot of efforts have been put in the area. The phenomenon of different objects with same spectrum is one of the problems, which often decreases the accuracy of classification based on spectral feature when we extract roads. In order to avoid this problem, the paper proposes the method that spectral feature and shape feature are all used to identify the road. The shape feature of the road is described by three shape parameters in this paper. The experimentation uses the image coming from the fusion of multispectral and panchromatic data. After the image is classified based on spectral feature, the objects that have same spectrum with road are removed in the classified image because their shape parameters are not like road' s shape parameters. According to the result of experimentation, the proposed approach can extract the main roads in the image effectively.

针对从遥感影像上提取道路,目前已经有很多研究,但尚有许多问题有待解决。如果仅从光谱特征分类入手提取道路,会存在“异物同谱”问题。为解决这个问题,提出了用光谱特征与形状特征相结合的方法提取道路。提出了3个形状指数描述道路的形状特征。以SPOT卫星影像为例,将高空间分辨率的全色图像与多光谱图像融合,首先基于道路光谱特征进行图像分类,然后再应用道路的形状特征去除分类图像中的“异物”目标。研究结果表明该方法能有效地从遥感影像中提取主干道路。

高分辨率遥感影像为用户提供了丰富的地表细节信息,如何利用图像分析技术从高分辨率遥感影像中进行目标提取,更新地理信息数据库,成为遥感信息处理研究的热点.采用面向对象分类法进行城市道路提取方法研究.首先,对影像进行分割获取影像对象,再通过对影像中道路特征的分析,利用影像对象的光谱特征、几何特征和空间关系建立知识库,最后,利用知识库中的规则来提取影像中的道路.以厦门某城区高分辨率影像进行了道路信息的自动提取实验,其面积一致性总体精度为88% ,形状一致性总体精度为90.13%.结果表明,面向对象法对于城市道路的提取和更新应用,具有一定的实际意义和推广性.

There has been a lot of methods that withdraw the road from remotely sensed image，such as image segmentation，road characteristic identifying basing on knowledge and morphology.But there are still many problems need to be resolved.This text carried out an algorithm.The first step involves road image two values，removing noise data，edge examination and edge conjunction using morphology.Through experiments using the ETM+data，this algorithm have a better anti-noise ability and higher accuracy，comparing with the traditional algorithm that edge detecting and edge conjunction.This algorithm has a certainly realistic meaning.

利用遥感图像进行道路提取已经有了一些研究，如图像分割，基于知识的道路特征识别和数学形态学等，但尚有许多问题需要解决，设计了一种基于数学形态学的遥感图像道路提取算法。该算法首先将遥感图像二值化，然后进行噪声滤除、形态学边缘检测与边缘连接。通过采用ETM+遥感图像进行实验表明，该算法与传统的边缘检测与边缘闭合的算法相比，具有更好的抗噪能力，且精度较高，具有一定的现实意义。

从遥感影像上提取道路面临如下问题:根据光谱特征分类的图像存在建筑物与道路混淆,受交通工具、行道树等影响易产生道路中的孔洞与道路边缘的毛刺等.该文利用南京市IKONOS高分辨率影像丰富的空间纹理信息,将纹理信息加入原始波段参与分类,可以解决建筑物与道路的混淆问题.另外,道路具有丰富的形态特征,应用数学形态学的相关算法和形状指数,可以很好地去除道路提取过程中产生的各种噪声.