Road Extraction Using Airborne LiDAR Data in Mountainous Areas

Based on the spatial distribution and characteristics of LiDAR points cloud of roads in mountainous areas，an effective method for road extraction from airborne LiDAR data is proposed in this research.First，the morphological filtering method is applied to remove above\|ground points cloud (such as buildings，transmission lines and vegetation etc.).Second，a region growing algorithm with multiple rules is used to extract and optimize the road points cloud.Finally，the road boundaries are located and tracked by using Freeman chain code method.Moreover，the mathematical morphology refining processing is used to extract the central line of mountainous road.The experimental results show that the proposed method is effective to extract road information in mountainous areas，and the completeness，accuracy and quality are 93.87%，93.84％，88.43％，respectively.     

基于QuickBird影像城市道路特征语义信息提取

快速、准确地获取城市道路信息,对于城市GIS数据更新具有重要意义。以昆明市为研究区,采用QuickBird卫星影像为数据源,开展了城市道路信息提取的特征语义信息提取实验研究。结果表明:①引入人脑认知OAR模型,提出高分辨率遥感影像城市道路认知框架,建立了道路信息提取语义模型,用数学方法和逻辑规则语言表达道路语义模型,再进行特征语义信息提取的研究思路是可行的;②采用Canny算子进行边缘检测道路、道路特征点细化、基于结点的线段追踪,进而提取对象语义信息、空间关系语义信息、局部上下文语义信息,最后通过GIS对提取的道路网络优化,实现道路网络最终提取,经检验提取道路信息长度的准确率为89.19%,宽度的准确率为71.54%,道路提取完整率为50.32%。     

纹理与几何特征在道路提取中的应用

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。     

基于全卷积神经网络的多源高分辨率遥感道路提取

针对半自动道路提取方法人工参与较多、提取精度不高且较为耗时的问题提出一种基于全卷积神经网络（FCN）的多源高分辨率遥感道路提取方法。首先,对高分二号和World View图像进行分割,用卷积神经网络（CNN）分类出包含道路的图像;然后,用Canny算子提取道路的边缘特征信息;最后,结合RGB、Gray和标签图放入FCN中训练,将现有的FCN模型拓展为多卫星源输入及多特征源输入的FCN模型。选取西藏日喀则地区作为研究区域,实验结果显示,所提方法在对高分辨率遥感影像进行道路提取时能够达到99.2%的提取精度,并且有效地减少了提取所需的时间。     

一种新的高分辨率SAR图像道路提取算法

针对高分辨率SAR图像中道路目标难以有效提取的问题,提出一种新的高分辨率SAR图像道路提取算法,它结合了参数化内核图割和数学形态学算法。利用参数化内核图割对高分辨率SAR图像中的道路目标进行初级分割,用数学形态学填充空洞,平滑道路边缘;基于道路的几何特征,使用矩阵度、改进的长宽比、复杂度等因子去除虚警;针对处理过程中出现的道路断裂情况,利用数学形态学提取道路目标的中心线,同时根据线段邻近性、方向一致性准则对其断裂部分进行连接,用数学形态学还原道路宽度,得到道路提取结果。实验结果表明该算法不用进行SAR图像预处理,也可以有效抑制相干斑噪声,并且能准确、较为完整地提取道路目标。     

Road centreline extraction from high‐resolution imagery based on multiscale structural features and support vector machines

This paper investigates road centreline extraction from high‐resolution imagery. A novel road detection system is proposed based on multiscale structural features and support vector machines (SVMs). The salient aspects of the strategy are: (1) structural features are exploited because road objects are narrow and extensive, with large perimeters and small radii; (2) the object‐based approach is used to extract multiscale information so as to reduce the local spectral variation caused by vehicles, shadows, road markings, etc.; (3) the hybrid spectral–structural features are analysed using the SVM classifier; and (4) multiple object levels are integrated because a multiscale approach can exploit the rich spatial information and detect multiscale road objects. Experiments were conducted on two IKONOS multispectral datasets and the results validated the proposed method.     

高分辨率遥感影像道路线性要素识别

为有效从高分辨率遥感影像中自动提取道路,提出利用线性要素间的拓扑关系识别道路线性要素的方法。提取影像中的线性要素并获取其邻域的光谱属性形成有向直线段;利用提出的道路线性要素识别模型,将满足条件的有向直线段聚类生成道路要素集;利用先验知识进一步验证。该方法主要使用道路线性要素的结构信息,适用于大范围、场景复杂的遥感影像,具有较高鲁棒性,目前该方法已应用于基于高分辨率遥感影像的GPS导航道路数据的生产和更新。     

The recognition of road network from high‐resolution satellite remotely sensed data using image morphological characteristics

With the development of remote sensors and satellite technologies, high‐resolution satellite data such as IKONOS images have been available recently. By these new high‐resolution satellite data, remote sensing technologies can be successfully applied to more application areas such as extracting road network from high‐resolution satellite images. This paper proposes a newly developed approach to extract a road network from high‐resolution satellite images. The approach is based on the binary and greyscale mathematical morphology and a line segment match method. First, the outline of road network is detected based on the grey morphological characteristics. Then, the basic road network is detected by the line segment match method. Next, the detected basic road network is processed based on the knowledge about the roads and binary mathematical morphological methods. Finally, visual analysis and three indicators are used to evaluate the accuracy of the extracted road networks. The results of the accuracy evaluation demonstrate that the developed road network extraction approach can provide both good visual effect and high positional accuracy.     

基于模糊连接度的高分辨率SAR图像道路自动提取

针对高分辨率合成孔径雷达(SAR)图像受到乘性斑点噪声的影响,且道路环境复杂多变的问题,提出一种基于模糊连接度的高分辨率SAR图像道路自动提取方法。首先,对SAR图像进行斑点滤波,以降低斑点噪声的影响;其次,结合指数加权均值比(ROEWA)算子检测结果和模糊C均值(FCM)分割结果自动提取种子点,从而提高自动化程度;最后,利用以图像灰度和ROEWA检测算子边缘强度为特征的模糊连接度算法对种子点进行扩展提取道路,经形态学处理后得到最终结果。对两幅SAR图像进行实验,并与FCM方法分割出的道路结果进行比较,所提出的方法在提取完整率、正确率及检测质量上均优于模糊C均值方法。实验结果表明,所提出的方法能较有效地从高分辨率SAR图像中提取不同宽度和弯曲程度的道路,且无需人工输入种子点。     

Research on Extraction Method of Coastal Aquaculture Areas on High Resolution Remote Sensing Image based on Multi-features Fusion

Coastal aquaculture areas are the important marine disaster bearing body，it is of great significance to carry out the research about automatically extraction aquaculture areas based on remote sensing for master basic information of coastal areas，mitigation and prevention of marine disasters.Used Gaofen-2 images for experimental data，and chose Dongshan Island sea in Fujian province as the experimental area，on the basis of analyzed the spectral characteristics of the aquaculture areas，construct feature index to extract spectral feature，used gray-level co-occurrence matrix method to extract the texture feature of the aquaculture areas，fused spectral features and texture features after feature selection，then used Otsu method to determine the threshold for raft culture area and fishing cage culture area，to achieve high precision intelligent extraction and classification for coastal aquaculture areas.The extraction accuracy of the raft culture area is more than 80%，and the extraction precision of the fish cage culture area is above 90%，and the overall extraction precision of the culture area is up to 87%.     

高分辨率遥感影像中道路震害信息的识别方法

大地震之后,紧急救援物资运输迫切需要了解灾区道路的震害信息,然而当前对遥感影像中道路的震害信息提取大多是基于像素的,提取的精度普遍不高。提出了一种面向对象的道路震害信息提取方法,通过综合利用道路的多种影像特征及震前GIS矢量道路相结合来提取道路,然后依据提取道路的完整程度来识别道路震害信息。采用汶川灾区的遥感影像为例进行了实验,与目视判读的结果比较后证明该方法有效改善了信息提取的速度和精度。     

一种高斯混合模型组合分类的机载LiDAR城区道路提取方法

城区道路自动提取一直是遥感领域研究的重点和热点之一。针对遥感影像提取易受建筑物和植被遮挡的影响,点云数据提取道路边界又较模糊的不足,提出了一种高斯混合模型组合分类的道路提取方法。该方法利用融合影像即含有色彩信息的点云数据,首先对滤波后点云中的反射强度属性,运用偏度平衡法粗提取道路点云;再对点云数据中的灰度信息和点密度属性采用高斯混合模型组合分类提取道路的种子区域,并利用强度影像扩展和约束该区域;最后运用主动轮廓法和数学形态学方法进一步优化并提取道路中心线。为验证该方法的有效性,分别采取位于国外某城市的两组LiDAR点云数据进行实验。结果表明,该方法可以有效地减弱阴影遮挡对道路提取的影响,提取的道路中心线较为平滑,道路的提取质量达到85%以上。     

High-resolution Remote Sensing Image Road Extraction Method for Improving U-Net

Accurate and efficient extraction of road information based on remote sensing image is a great significance for the establishment and maintenance of basic geographic databases. Due to the complex background information of high-resolution remote sensing images, existing algorithms cannot extract road information very well. U-Net network has good experimental results in image segmentation, but the accuracy of road segmentation results is not good. For this reason, this paper proposes a high-resolution image road extraction method based on improved U-Net network. Firstly, the U-Net-based network structure is designed and implemented. The network uses VGG16 as the network coding structure, which can extract feature semantic information better. Secondly, the use of Batch Normalization and Dropout solves the phenomenon of over-fitting that occurs during the network training process. Finally, the training data is expanded by rotation and mirror transformation, and the ELU activation function is used to improve the network training speed. The experimental results show that the method can extract road information more accurately and efficiently.     

一种改进U-Net的高分辨率遥感影像道路提取方法

从遥感影像中准确高效地提取道路信息,对基础地理数据库的建立与维护具有重大意义。高分辨率遥感影像背景信息复杂,导致现有算法无法较好地从中提取道路信息。U-Net网络在图像分割方面有较好的实验效果,但道路分割结果准确性不佳,因此,提出了一种改进U-Net网络的高分辨率影像道路提取方法。首先,设计基于U-Net的网络结构,将VGG16作为网络编码结构,可更好地提取特征语义信息;其次,利用Batch Normalization与Dropout解决网络训练过程中出现的过拟合;最后,对训练数据利用旋转与镜像变换进行扩充,采用ELU激活函数,提升了网络训练速度。实验结果表明：该方法可以较为准确高效地提取道路信息。     

面向对象的高分辨率遥感影像数据的道路提取流程——地理国情普查数据的自动提取

为了提高地理国情普查数据生产的自动化程度,针对高分辨率遥感影像的特征,以道路为例,基于面向对象的思想构建了一套通用性较高的数据提取方法流程,并以北京门头沟、河南郑州市作为实验区,证实自动提取规则的有效性。研究结果表明,郊区道路的自动化提取精度比城区道路更高;大比例尺基础数据的引入,可屏蔽掉缓冲区外非道路要素的干扰,提高分类精度。     

基于数学形态学的道路遥感影像特征提取及网络分析

如何从遥感图象上提取道路特征已有多种方法，如边缘探测与追踪、线性滤波、利用各种空间关系进行道路特征识别，基于知识的道路网络提取以及数学形态学等，但尚有许多问题有待解决。为了方便GIS应用以及地图更新，提出了一种基于数学形态学的道路网络分析方法，用于对遥感图象上已分类的道路信息进行各种处理，以便得到所需的道路网络。该方法与步骤为首先将道路影像二值化，同时进行噪音去除、断线连接、细化，并通过将栅格数据转换成矢量形式来得到基本的道路网络；然后对基本道路网络进行分析、连接、选取；最后用Douglas-Peuker算法对道路进行平滑处理与表示来得到最终提取的道路网络，并以南京市江宁经济开发区SPOT、高分辨率IKONOS图象为例进行了实验。道路特征提取的结果与目视解译结果进行比较的结果表明，该道路提取方法对道路发展相对较快的区域更为有效，且提取精度较高。该方法对土地管理规划部门非常有价值，是进行GIS与地图道路更新的有效方法。     

The Comparison of Urban Tree Crown Extraction based on Airborne LiDARElevation Difference and High Resolution Imagery

With the support of airborne Light Detection and Ranging (LiDAR) data and high spatial resolution aerial imagery,this paper presents an individual tree extraction method that takes the region of urban as the study area.The elevation difference model originated from LiDAR data was used to extract regions of interest including trees. Then,masking was applied to the high spatial resolution aerial imagery to get the same regions. Besides,image segmentations,based on the marked watershed algorithm,were processed on the high spatial resolution aerial imagery and the elevation difference model separately to extract individual tree crowns. Finally,we took a visual interpretation to delineate tree crowns manually and this result was regarded as the reference crowns map. The extraction accuracies were assessed by comparing the spatial relationships of the reference crowns and the automated delineated tree crowns based on the elevation difference model and the high resolution imagery. The results show that the LiDAR data is developed to improve the efficiency of obtaining forest region that the canopy height model include 85.25% forest information. In addition,the tree crowns extraction accuracy based on the high resolution aerial imagery is 57.14%,while another extraction accuracy based on the elevation difference model is 42.47%,which indicated that the marked watershed algorithm proposed in this paper is effective and the high resolution imagery is better than the elevation difference model to extract tree crowns.     

基于PPMU-net的多特征高分辨率遥感道路提取

针对复杂地形条件下道路特征选取不具代表性,分割精度低的问题,提出了一种基于卷积神经网络（PPMU-net）的高分辨率遥感道路提取的方法。将3通道的高分二号光谱信息与相应的地形信息（坡度、坡向、数字高程信息）进行多特征融合,合成6通道的遥感图像;对多特征的遥感图像进行切割并利用卷积网络（CNN）筛选出含道路的图像;将只含道路的遥感图像送进PPMU-net中训练,构建出高分辨率遥感图像道路提取模型。在与U-net神经网络、PSPnet神经网络相比时,所提的方法在对高分辨率遥感道路提取时能够达到较好的效果,提高了复杂地形条件下道路分割的精度。     

基于无人机影像的烟草精细提取

烟草是一种特殊农作物，烟草的提取对其信息统计起着重要作用。针对烟草单株提取难的问题，提出了一种结合多特征和超像素的无人机影像烟草精细提取方法。首先利用简单线性迭代聚类 （Simple Linear Iterative Clustering， SLIC）算法对影像进行超像素分割；然后统计超像素的平均值、亮度、长宽比、形状指数、红绿蓝波段值和自定义植被指数；接着通过对超像素特征组合和特征阈值选取来实现烟草的精细提取；最后对提取信息进行统计和分析。实验结果表明：该方法能有效地提取烟草株树，准确度分别为99%和98.6%。利用该方法，在计算烟草产量方面供了有效参考，节省了大部分的人力财力。     

利用Deeplab v3提取高分辨率遥感影像道路

针对传统道路提取方法存在的道路边缘粗糙、抗干扰性弱、提取精度低等问题,提出了一种基于编码解码器的空洞卷积模型(Deeplab v3)的道路提取方法。首先,对原始高分辨率遥感影像进行标注;其次,利用标注数据集对Deeplab v3模型进行训练、测试;最后,得到高分辨率遥感影像道路提取结果。分析结果可知,该模型能够较好地提取高分辨率遥感影像中的道路边缘特征,相比其他道路提取方法具有更高的提取精度和更加完整的道路信息,正确率可达到93%以上。