Accuracy test of point-based and object-based urban building feature classification and extraction applying airborne LiDAR data

Point-based and object-based building extractions were conducted in airborne LiDAR data in a sample area of Buffalo, New York. First, the earth surface points were filtered from the entire laser scan data set using a new filtering algorithm, which combines the TIN slope modelling and statistical analysis. The off-ground points were extracted for buildings in the study area using both point cluster analysis and object-oriented classifications. The accuracies of both approaches were tested using the digitised ground truth. The outcomes of accuracy testing of the point-based method are correctness: 88.74%, completeness: 92.67% and quality: 83.50%. The results of the accuracy of object-based building extraction are correctness: 87.21%, completeness: 60.14%, and quality: 55.26%. Reconstructions of 3D building models based on the extracted building points were performed. This study contributes scientific and technological knowledge for researchers in developing more effective methods in converting the LiDAR survey to a 3D GIS database.     

动态空间正图像透视投影正反解

卫星图像都是在动态情形下获取的。瞬间曝光获取的图像投影性质符合透视投影。本文针对卫星动态获取的正图像,建立其平面透视投影,利用矢量解法研究其正反解变换和星下点坐标计算方法,最后给出了算例。     

利用层间连接和平滑策略重建屋顶三维模型

面向数字城市和智慧城市建设急需城市建筑三维模型支撑的需要,本文基于机载Li DAR数据,以"顾及平整性的屋顶面片分割—屋顶层间连接—三维模型重建"为脉络,提出了一种采用层间连接和平滑策略的建筑屋顶三维模型重建方法。在屋顶面片提取过程中,充分顾及了屋顶面片的平整性;并在屋顶面片平整基础上,提出层间连接点的概念,以实现高效、快速的模型重建工作。试验部分,本文从屋顶面片重建完整率与正确率、重建几何精度及建筑物高程对于重建的影响3个方面作了较为详尽的评价与分析,并在国际摄影测量与遥感学会标准数据集支撑下,与国际同行进行试验对比。试验结果表明,建筑屋顶重建的完整率和正确率分别达到90%和95%;在偏移距离评价方面,平均偏移距离和标准差最优分别达0.05 m和0.18 m。因此,本文方法可有效完成建筑屋顶三维模型重建,重建模型准确度高、完整性好。     

Automatic Building Extraction from Image and LiDAR Data with Active Contour Segmentation

Automatic building extraction is an important topic for many applications such as urban planning, disaster management, 3D building modeling and updating GIS databases. Its approaches mainly depend on two data sources: light detection and ranging (LiDAR) point cloud and aerial imagery both of which have advantages and disadvantages of their own. In this study, in order to benefit from the advantages of each data sources, LiDAR and image data combined together. And then, the building boundaries were extracted with the automated active contour algorithm implemented in MATLAB. Active contour algorithm uses initial contour positions to segment an object in the image. Initial contour positions were detected without user interaction by a series of image enhancements, band ratio and morphological operations. Four test areas with varying building and background levels of detail were selected from ISPRS’s benchmark Vaihingen and Istanbul datasets. Vegetation and shadows were removed from all the datasets by band ratio to improve segmentation quality. Subsequently, LiDAR point cloud data was converted to raster format and added to the aerial imagery as an extra band. Resulting merged image and initial contour positions were given to the active contour algorithm to extract building boundaries. In order to compare the contribution of LiDAR to the proposed method, the boundaries of the buildings were extracted from the input image before and after adding LiDAR data to the image as a layer. Finally extracted building boundaries were smoothed by the Awrangjeb (Int J Remote Sen 37(3): 551–579.  https://doi.org/10.1080/01431161.2015.1131868, 2016) boundary regularization algorithm. Correctness (Corr), completeness (Comp) and accuracy (Q) metrics were used to assess accuracy of segmented building boundaries by comparing extracted building boundaries with manually digitized building boundaries. Proposed approach shows the promising results with over 93% correctness, 92% completeness and 89% quality.     

Object based building footprint detection from high resolution multispectral satellite image using K-means clustering algorithm and shape parameters

Object-based image analysis (OBIA) has been a new area of research in satellite image processing applications, since it improves the quality of information acquisition about geospatial objects and also enables to add spatial and contextual information to the objects of interest. The extraction of buildings from High Resolution Satellite (HRS) image in an urban scenario has been an intricate problem due to their different size, shape, varying rooftop textures and low contrast between building and surrounding region. In this study, a new object-based automatic building extraction technique has been proposed to extract building footprints from HRS pan sharpened IKONOS multispectral image. The study is mainly emphasizing on obtaining optimal values for segmentation parameters, shape parameters, and defining rule set to extract buildings and eliminate misclassified other urban features. The suitability of the technique has been judged using different indicators, such as, completeness, correctness and quality.     

机载LiDAR点云的多层建筑物三维轮廓模型自动重建

以机载LiDAR点云数据为研究对象,提出一种新的基于点云数据的多层建筑物三维轮廓模型高精度自动重建方法。在已完成建筑物结构提取及轮廓规则化处理的基础上,利用多层屋顶轮廓在水平投影面内的相邻关系,将各层屋顶中同等级屋顶的相邻关系概括为平行边、不平行且不相交、相交3种相邻形式,结合多层屋顶的层级结构信息对相邻轮廓边界进行一致性处理。实验证明本文方法可以进一步消除多层建筑物各屋顶轮廓的规则化处理误差,使相邻轮廓边界在水平投影面内严格重合,同时重建后建筑物三维轮廓模型的正确性与完整性较高,拐点的定位精度优于激光点平均间距。     

面向对象的形态学建筑物指数及其高分辨率遥感影像建筑物提取应用

高分辨率遥感影像建筑物提取是摄影测量与遥感领域的一个热门研究主题。本文综合利用影像分割、基于图的数学形态学top-hat重建技术,提出了面向对象的形态学建筑物指数OBMBI,并将其应用于高分辨率遥感影像建筑物提取。首先,建立像素-对象-图节点的双向映射关系;然后,基于图的白top-hat重建和上述映射关系来构建OBMBI图像;接着,对该OBMBI图像二值化、矢量化以获取建筑物多边形;最后,对结果进行后处理优化。使用一景航空、一景卫星全色影像对本文方法和PanTex方法进行性能测试。试验表明,本文方法的建筑物提取精度显著的优于PanTex方法。其中,本文方法平均比PanTex方法的正确率高9.49%、完整率高11.26%、质量高14.11%。     

多尺度邻域特征下的机载LiDAR点云电力线分类

利用机载激光雷达技术三维测量精度高且获取快速的优点进行电力线自动分类提取已成为点云数据处理与电力应用的重要领域。针对电力线分类模型的自动化和高精度需求,本文提出了基于三维多尺度邻域特征的机载LiDAR点云电力线分类提取模型框架,主要包括4个步骤：电力线候选点滤波、多尺度邻域类型选取、形状结构特征提取和支持向量机分类。通过对2个复杂城市区域的试验数据集和8种不同邻域类型的详细结果对比分析,发现基于多尺度圆球邻域形状结构特征的分类模型结果准确率、召回率和质量分别达到97%、94%和93%,同时整体处理时间在2个试验数据中分别从366、256 s减少到274、160 s。试验结果表明,该方法在多种复杂城市场景中能够实现机载LiDAR数据的电力线较高精度分类提取。     

Rural Road Surface Extraction Using Mobile LiDAR Point Cloud Data

The existing roadway infrastructures are mostly archived with two-dimensional (2D) drawings that lack the possibility for three-dimensional (3D) interpretation and advanced 3D analysis. The mobile LiDAR system (MLS) is gaining popularity in 3D mapping applications along various types of road corridors. MLS achieves the highest data quality and completeness among the traditional roadway data collection methods. The rural roads in different countries especially in India form a substantial portion of the road network. Therefore the proper maintenance and road safety analysis of rural roads are recommended activity, which could be addressed using detailed 3D road surface information. The absence of raised curb at road boundary, and presence of complexity, heterogeneity and occlusions along the rural roadway settings restrict the use of existing studies for road surface extraction using MLS point cloud data. Therefore considering the above requirement, this research paper proposes a two-stage method. The first stage extract planar ground surfaces which are further used to filter road surface in the second stage. Global properties of road, that is, topology and smoothness and its radiometric response to laser beam of MLS are used in the second stage. MLS point cloud data of rural roadway were used to test the proposed method. The road surface points were accurately extracted without being affected by the absence of raised curb and hanging objects over the road surface, that is, tree canopies and overhead power lines. The quantitative assessment of the proposed method was performed in terms of correctness, completeness and quality, which were 96.3, 94.2, and 90.9%, respectively.     

利用目标区域拓扑关系图提取建筑物点云

建筑物提取一直是机载激光点云数据处理研究的热点,其中建筑物和其他地物之间的区分是研究的核心和难点。为提高建筑物与其他地物在机载激光点云中的区分能力,提出了一种建筑物点云层次提取方法。首先,在点云滤波后,从非地面点云中提取建筑物候选区域;然后,通过形态学重建和点云平面分割方法对建筑物候选区域构建多尺度空间,并建立目标区域的拓扑关系图;最后,在拓扑关系图基础上,利用5种特征量对目标区域分类,并精确提取建筑物点云。为了测试算法的有效性和可靠性,利用国际摄影测量与遥感学会（International Society for Photogrammetry and Remote Sensing,ISPRS）提供的Vaihingen和Toronto两组测试数据集进行实验,并由ISPRS对结果进行评估,其中基于面积和目标的完整度、正确率和提取质量分别都大于87.8%、94.7%、87.3%。与其他建筑物提取方法相比,该方法在基于面积和目标的质量指标方面最为稳定。实验结果表明,在不同的城市场景下,该算法能够稳健地提取建筑物,并保持很高的正确率。     

半自动机载LiDAR点云建筑物三维重建方法

针对全自动建筑物3D重建存在需要后续人工检验,且发现重建错误需要花费额外时间修改的问题,提出了一种半自动的面向对象的机载LiDAR点云建筑物3D重建方法。基于建筑物类别点云的联通分析和平面生长分割结果,提出了自动的建筑物栋数检测、单栋建筑物外轮廓提取、单栋建筑物内部结构线提取方法;同时,在计算机无法完成部分工作时,人工辅助计算机完成高程阶越线提取、识别建筑物屋顶附属物点云等工作。实验证明,该方法可以适用于高密度机载LiDAR点云数据中城区大部分建筑物的3D模型重建。     

Remote Sensing Data Reveals Eco-Environmental Changes in Urban Areas of Klang Valley, Malaysia: Contribution from Object Based Analysis

Understanding the growth and changes in urban environments are the most dynamic system on the earth’s surface is critical for urban planning and sustainable management. This study attempts to present a space-borne satellite-based approach to demonstrate the urban change and its relation with land surface temperature (LST) variation in urban areas of Klang valley, Malaysia. For this purpose an object-based nearest neighbour classifier (S-NN) approach was first applied on SPOT 5 data acquired on 2003 and 2010 and subsequently five land cover categories were extracted. The overall accuracies of the classified maps of 2003 and 2010 were 90.5 % and 91 % respectively. The classified maps were then used as inputs to perform the post classification change detection. The results revealed that the post-classification object-based change detection analysis performed reasonably well with an overall accuracy of 87.5 %, with Kappa statistic of 0.81 %. The changes represented that the urban expanded by 10 % over the period, whereas the urban expansion had caused reduction in soil (1.4 %) and vegetation (11.4 %), and growth in oil palm (2 %), and water (0.7 %). Additionally decision tree method was used to derive the surface heat fluxes from thermal infrared Landsat TM and ETM+bands. Subsequently, a comparison was made with classified result from SPOT 5 images. Results showed high correlation between urban growth and LST.     

Pixel-based and object-based classifications using high- and medium-spatial-resolution imageries in the urban and suburban landscapes

With the increasing availability of high-spatial-resolution remote sensing imageries and with the observed limitations of pixel-based techniques, the development and testing of geographic object-based image analysis (GEOBIA) techniques for image classification have become one of the main research areas in geospatial science. This paper examines and compares the classification performance of a pixel-based method and an object-based method as applied to high- (QuickBird satellite image) and medium- (Landsat TM image) spatial-resolution imageries in the context of urban and suburban landscapes. For the pixel-based classification, the maximum-likelihood supervised classification approach was employed. And for the object-based classification, the pixel-based classified maps were integrated with a set of image segments produced using various calibrations. The results show evidence that the object-based method can produce classifications that are more accurate for both high- and medium-spatial- resolution imageries in the context of urban and suburban landscapes.     

基于自适应图像分割自动提取道路中心线

道路是城区地理空间信息中最重要的基础设施之一,从高分辨影像中自动、快速的提取道路特征,是快速更新城市道路网信息的重要途径。文中在分析道路基本特征的基础上,选择基于自适应结构元素的形态分析算法提取初始道路区域;引入面积和长宽比等形状指数,得到较精确的道路信息;最后,采用Hilditch细化算法,并进行优化处理。实验证明,该道路提取过程中无需人工设置参数,且能够得到具有较高完整性和正确性的道路中心线。     

Automatic Registration Between Low-Altitude LiDAR Point Clouds and Aerial Images Using Road Features

Among the many means of acquiring surface information, low-altitude light detection and ranging (LiDAR) systems (e.g., unmanned aerial vehicle LiDAR, UAV-LiDAR) have become an important approach to accessing geospatial information. Considering the lower level of hardware technology in low-altitude LiDAR systems compared to that in airborne LiDAR, and the greater flexibility in-flight, registration procedures must be first performed to facilitate the fusion of laser point data and aerial images. The corner points and edges of buildings are frequently used for the automatic registration of aerial imagery with LiDAR data. Although aerial images and LiDAR data provide powerful support for building detection, adaptive edge detection for all types of building shapes is difficult. To deal with the weakness of building edge detection and reduce matching-related computation, the study presents a novel automatic registration method for aerial images, with LiDAR data, on the basis of main-road information in urban areas. Firstly, vector road centerlines are extracted from raw LiDAR data and then projected onto related aerial images with the use of coarse exterior orientation parameters (EOPs). Secondly, the corresponding image road features of each LiDAR vector road are determined using an improved total rectangle-matching approach. Finally, the endpoints of the conjugate road features obtained from the LiDAR data and aerial images are used as ground control points in space resection adjustment to refine the EOPs; an iterative strategy is used to obtain optimal matching results. Experimental results using road features verify the feasibility, robustness and accuracy of the proposed approach.     

Integration of high-resolution imagery and LiDAR data for object-based classification of urban area

This paper investigates the synergistic use of high-resolution multispectral imagery and Light Detection and Ranging (LiDAR) data for object-based classification of urban area. The main contribution of this paper is the development of a semi-automated object-based and rule-based classification method. In the implemented approach, the diverse knowledge about land use/land cover classes are transformed into a set of specialized rules. Further, this paper explores supervised Gaussian Mixture Models for classification, which have been primarily used for unsupervised classification. The work is carried out on test data from two different sites. Contribution of the LiDAR data resulted in a significant improvement of overall Kappa. Accuracy assessment carried out for aforementioned classification methods shows higher overall kappa for both the study sites.     

Mapping 3D visibility in an urban street environment from mobile LiDAR point clouds

ABSTRACT

Visibility determination is a key requirement in a wide range of national and urban applications, such as national security, landscape management, and urban design. Mobile LiDAR point clouds can depict the urban built environment with a high level of details and accuracy. However, few three-dimensional visibility approaches have been developed for the street-level point-cloud data. Accordingly, an approach based on mobile LiDAR point clouds has been developed to map the three-dimensional visibility at the street level. The method consists of five steps: voxelization of point-cloud data, construction of lines-of-sight, construction of sectors of sight, construction of three-dimensional visible space, and calculation of volume index. The proposed approach is able to automatically measure the volume of visible space and openness at any viewpoint along a street. This approach has been applied to three study areas. The results indicated that the proposed approach enables accurate simulation of visible space as well as high-resolution (1 m × 1 m) mapping of the visible volume index. The proposed approach can make a contribution to the improvement of urban planning and design processes that aim at developing more sustainable built environments.     

融合高分影像和LiDAR数据的城市道路提取

为避免由于城市道路复杂及树木建筑的阴影遮挡导致从遥感影像中提取道路信息不准确的问题,本文采用高分影像和Li-DAR数据相融合的方法实现城市道路的提取,并使用一种基于最小面积外接矩形(MABR)的后处理改进方法进行完善.首先对试验区进行数据配准;然后应用FNEA算法进行图像分割,并使用随机森林分类法进行分类,将影像融合和...     

Object-oriented semantic labelling of spectral–spatial LiDAR point cloud for urban land cover classification and buildings detection

The urban land cover mapping and automated extraction of building boundaries is a crucial step in generating three-dimensional city models. This study proposes an object-based point cloud labelling technique to semantically label light detection and ranging (LiDAR) data captured over an urban scene. Spectral data from multispectral images are also used to complement the geometrical information from LiDAR data. Initial object primitives are created using a modified colour-based region growing technique. Multiple classifier system is then applied on the features extracted from the segments for classification and also for reducing the subjectivity involved in the selection of classifier and improving the precision of the results. The proposed methodology produces two outputs: (i) urban land cover classes and (ii) buildings masks which are further reconstructed and vectorized into three-dimensional buildings footprints. Experiments carried out on three airborne LiDAR datasets show that the proposed technique successfully discriminates urban land covers and detect urban buildings.     

Mapping fuels at the wildland-urban interface using colour ortho-images and LiDAR data

Fuel type mapping of the wildland-urban interface (WUI) in support of fire spread simulation modelling should include both natural and urban features. The objective of this study was to evaluate the utility of (1) Light Detection and Ranging (LiDAR) structural data, (2) ortho-image data and (3) a combination of both as input to an object-based classification approach for mapping fuels within two WUI areas in San Diego, California. A separability analysis was utilized to determine the surface topographical and spectral layers most influential for discriminating WUI fuels. An accuracy assessment revealed that the combination of LiDAR and ortho-image data inputs substantially increased classification accuracy by 20–30% and achieved overall accuracies?>?80%. Results from the study provide knowledge on how reliable fuel types within the WUI can be mapped using high-resolution LiDAR and ortho-image data while presenting new insights into fuel type mapping.