结合体元数据结构的机载LIDAR建筑物检测

目的 目前,点云、栅格格网及不规则三角网等建筑物检测中常用的离散机载激光雷达（LIDAR）点云数据表达方式存在模型表达复杂、算法开发困难、结果表达不准确及难以表达多返回数据等缺点。为此,针对LIDAR点云体元结构模型构建及在此基础上的建筑物检测展开研究,提出一种基于体元的建筑物检测算法。方法 首先将点云数据规则化为二值（即1、0值,分别表示体元中是否包含有激光点）3D体元结构。然后利用3D滤波算法将上述体元结构中表征数据点的体元分类为地面和非地面体元。最后,依据建筑物边缘的接近直线、跳变特性从非地面体元中搜寻建筑物边缘作为种子体元进而标记与其3D连通的非地面体元集合为建筑物体元。结果 实验基于ISPRS（international society for photogrammetry and remote sensing）提供的包含了不同的建筑物类型的城区LIDAR点云数据测试了"邻域尺度"参数的敏感性及提出算法的精度。定量评价的结果表明：56邻域为最佳邻域尺度;建筑物的检测质量可达到95%以上——平均完整度可达到95.61%、平均正确率可达95.97%。定性评价的结果表明：对大型、密集、不规则形状、高低混合及其他屋顶类型比较特殊的复杂建筑物均可成功检测。结论 本文提出的建筑物检测算法采用基于体元空间邻域关系的搜索标记方式,可有效实现对各类建筑目标特别是城市建筑目标的检测,检测结果易于建模3D建筑物模型。     

Multi-type change detection of building models by integrating spatial and spectral information

Detecting building changes followed by updates is preferable for efficient revisions to building models. Additionally, more change types can be detected with spatial information provided by building models for reducing land surveying work. Therefore, for efficient building of model revision and land surveys, this work applies a new multi-type change detection scheme with new light detection and ranging (LIDAR) point clouds, new aerial images and existing building models. By integrating the spatial information from LIDAR data and image-based spectral information, this work identifies changes to existing buildings and identifies newly built and changed buildings. To provide an initial value for further revisions, new building regions are generated from change detection results. Experimental results demonstrate that the proposed scheme has high accuracy for both change type determination and building region generation. To provide comprehensive observations, experimental results deemed unreliable are scrutinized.     

Comparison and fusion of LIDAR and InSAR digital elevation models over urban areas

In this paper we analyse a multiple sensor dataset corresponding to three-dimensional data coming from interferometric radar (InSAR) or laser ranging (LIDAR) measurements. We consider digital elevation models (DEMs) extracted from a single LIDAR scan plus multiple SAR scans of the same area, downtown Denver, CO, USA. Horizontal resolution for both datasets is 2.5?m, a value allowing good characterization of sparse tall buildings. Fusion of DEMs extracted from InSAR data originated during flights orthogonal to each other allows reduction of layover and shadowing. A novel strategy combining advantages of existing fusion techniques is proposed. Results from individual and combined techniques are presented, compared and discussed. The ability of characterizing buildings allows us to raise the fusion strategy scope from the pixel-level up to the feature level, once 3D features are extracted. Related results are presented and discussed.

Finally, fusion of InSAR and LIDAR data is considered. LIDAR can reliably determine building footprints, thus relieving the problem of multiple bouncing radar pulses. Some results show that analysis of combined InSAR and LIDAR data on a small area can provide an improvement in DEMs extracted from a much larger area where only InSAR data are available.     

Visual Analysis and Semantic Exploration of Urban LIDAR Change Detection

Many previous approaches to detecting urban change from LIDAR point clouds interpolate the points into rasters, perform pixel‐based image processing to detect changes, and produce 2D images as output. We present a method of LIDAR change detection that maintains accuracy by only using the raw, irregularly spaced LIDAR points, and extracts relevant changes as individual 3D models. We then utilize these models, alongside existing GIS data, within an interactive application that allows the chronological exploration of the changes to an urban environment. A three‐tiered level‐of‐detail system maintains a scale‐appropriate, legible visual representation across the entire range of view scales, from individual changes such as buildings and trees, to groups of changes such as new residential developments, deforestation, and construction sites, and finally to larger regions such as neighborhoods and districts of a city that are emerging or undergoing revitalization. Tools are provided to assist the visual analysis by urban planners and historians through semantic categorization and filtering of the changes presented.     

Synergistic use of QuickBird multispectral imagery and LIDAR data for object-based forest species classification

This study evaluated the synergistic use of high spatial resolution multispectral imagery (i.e., QuickBird, 2.4 m) and low-posting-density LIDAR data (3 m) for forest species classification using an object-based approach. The integration of QuickBird multispectral imagery and LIDAR data was considered during image segmentation and the subsequent object-based classification. Three segmentation schemes were examined: (1) segmentation based solely on the spectral image layers; (2) segmentation based solely on LIDAR-derived layers; and (3) segmentation based on both the spectral and LIDAR-derived layers. For each segmentation scheme, objects were generated at twelve different scales in order to determine optimal scale parameters. Six categories of classification metrics were generated for each object based on spectral data alone, LIDAR data alone and the combination of both data sources. Machine learning decision trees were used to build classification rule sets. Quantitative segmentation quality assessment and classification accuracy results showed the integration of spectral and LIDAR data, in both image segmentation and object-based classification, improved the forest classification compared to using either data source independently. Better segmentation quality led to higher classification accuracy. The highest classification accuracy (Kappa = 91.6%) was acquired when using both spectral- and LIDAR-derived metrics based on objects segmented from both spectral and LIDAR layers at scale parameter 250, where best segmentation quality was achieved. Optimal scales were analyzed for each segmentation-classification scheme. Statistical analysis of classification accuracies at different scales revealed that there was a range of optimal scales that provided statistically similar accuracy.     

激光点云提取建筑物平面目标算法研究

从激光点云中提取建筑物信息是当前遥感数据处理的热点与难点,而构成建筑物的平面以及轮廓线的提取是LIDAR数据处理和建筑物三维建模的关键技术。本文通过分析激光点云数据中建筑物的特征,综合点云滤波、KD树索引、三维Hough变换以及Gauss球法向量统计算法的各自优点,提出了一套建筑物平面及轮廓的自动提取算法,并通过实验验证了该算法的有效性。     

Urban scene understanding from aerial and ground LIDAR data

We present a framework to segment cultural and natural features, given 3D aerial scans of a large urban area, and (optionally) registered ground level scans of the same area. This system provides a primary step to achieve the ultimate goal of detecting every object from a large number of varied categories, from antenna to power plants. Our framework first identifies local patches of the ground surface and roofs of buildings. This is accomplished by tensor voting that infers surface orientation from neighboring regions as well as local 3D points. We then group adjacent planar surfaces with consistent pose to find surface segments and classify them as either the terrain or roofs of buildings. The same approach is also applied to delineate vertical faces of buildings, as well as free-standing vertical structures such as fences. The inferred large structures are then used as geometric context to segment linear structures, such as power lines, and structures attached to walls and roofs from remaining unclassified 3D points in the scene. We demonstrate our system on real LIDAR datasets acquired from typical urban regions with areas of a few square kilometers each, and provide a quantitative analysis of performance using externally provided ground truth.     

Creating 3D city models with building footprints and LIDAR point cloud classification: A machine learning approach

The increasing availability of open geospatial data, such as building footprint vector data and LiDAR (Light Detection and Ranging) point clouds, has provided opportunities to generate large-scale 3D city models at low cost. However, using unclassified point clouds with building footprints to estimate building heights may yield erroneous results due to potential errors and anomalies in both datasets and their integration. Some of the points within footprints often reflect irrelevant objects other than roofs, leading to biases in height estimation, and few studies have developed systematic methods to filter them out. In this paper, a LiDAR point classification methodology is proposed that extracts only rooftop points for building height estimation. The LiDAR points are characterized by point, footprint, and neighborhood-based features and classified by the Random Forest (RF) algorithm into four classes – rooftop, wall, ground, and high outlier. The percentage of correctly classified points among 15,577 sample points in Columbus, Ohio, amounts to 96.5%. Conducting this classification separately for different building types (commercial, residential, skyscraper, and small constructions) does not significantly change the overall accuracy. The footprint-based features contribute most to predicting the classes correctly. Height validation results based on a sample of 498 buildings show that (1) using average or median heights with classified points provides the best estimates, minimizing the disparities between computed heights and ground truth and (2) the RF method yields outcomes much closer to ground truth than earlier classification approaches. Some outcomes are visualized in 3D format using Google Earth 3D Imagery and ArcScene.     

Urban building reconstruction from raw LiDAR point data

We present a method for automatic reconstruction of the volumetric structures of urban buildings, directly from raw LiDAR point clouds. Given the large-scale LiDAR data from a group of urban buildings, we take advantage of the “divide-and-conquer” strategy to decompose the entire point clouds into a number of subsets, each of which corresponds to an individual building. For each urban building, we determine its upward direction and partition the corresponding point data into a series of consecutive blocks, achieved by investigating the distributions of feature points of the building along the upward direction. Next, we propose a novel algorithm, Spectral Residual Clustering (SRC), to extract the primitive elements within the contours of blocks from the sectional point set, which is formed by registering the series of consecutive slicing points. Subsequently, we detect the geometric constraints among primitive elements through individual fitting, and perform constrained fitting over all primitive elements to obtain the accurate contour. On this basis, we execute 3D modeling operations, like extrusion, lofting or sweeping, to generate the 3D models of blocks. The final accurate 3D models are generated by applying the union Boolean operations over the block models. We evaluate our reconstruction method on a variety of raw LiDAR scans to verify its robustness and effectiveness.     

多特征融合与几何卷积的机载LiDAR点云地物分类

目的点云分类传统方法中大量依赖人工设计特征,缺乏深层次特征,难以进一步提高精度,基于深度学习的方法大部分利用结构化网络,转化为其他表征造成了3维空间结构信息的丢失,部分利用局部结构学习多层次特征的方法也因为忽略了机载数据的几何信息,难以实现精细分类。针对上述问题,本文提出了一种基于多特征融合几何卷积神经网络(multi-feature fusion and geometric convolutional neural network,MFFGCNN)的机载Li DAR(light detection and ranging)点云地物分类方法。方法提取并融合有效的浅层传统特征,并结合坐标尺度等预处理方法,称为APD模块(airporne laser scanning point cloud design module),在输入特征层面对典型地物有针对性地进行信息补充,来提高网络对大区域、低密度的机载Li DAR点云原始数据的适应能力和基础分类精度,基于多特征融合的几何卷积模块,称为FGC(multi-feature fusion and geometric convolution)算子,...     

Complete residential urban area reconstruction from dense aerial LiDAR point clouds

We present an automatic system to reconstruct 3D urban models for residential areas from aerial LiDAR scans. The key difference between downtown area modeling and residential area modeling is that the latter usually contains rich vegetation. Thus, we propose a robust classification algorithm that effectively classifies LiDAR points into trees, buildings, and ground. The classification algorithm adopts an energy minimization scheme based on the 2.5D characteristic of building structures: buildings are composed of opaque skyward roof surfaces and vertical walls, making the interior of building structures invisible to laser scans; in contrast, trees do not possess such characteristic and thus point samples can exist underneath tree crowns. Once the point cloud is successfully classified, our system reconstructs buildings and trees respectively, resulting in a hybrid model representing the 3D urban reality of residential areas.     

Generation of a DTM and building detection based on an MPF through integrating airborne lidar data and aerial images

This study presents an approach that uses airborne light detection and ranging (lidar) data and aerial imagery for creating a digital terrain model (DTM) and for extracting building objects. The process of creating the DTM from lidar data requires four steps in this study: pre-processing, segmentation, extraction of ground points, and refinement. In the pre-processing step, raw data are transformed to raster data. For segmentation, we propose a new mean planar filter (MPF) that uses a 3 × 3 kernel to divide lidar data into planar and nonplanar surfaces. For extraction of ground points, a new method to extract additional ground points in forest areas is used, thus improving the accuracy of the DTM. The refinement process further increases the accuracy of the DTM by repeated comparison of a temporary DTM and the digital surface model. After the DTM is generated, building objects are extracted via a proposed three-step process: detection of high objects, removal of forest areas, and removal of small areas. High objects are extracted using the height threshold from the normalized digital surface model. To remove forest areas from among the high objects, an aerial image and normalized digital surface model from the lidar data are used in a supervised classification. Finally, an area-based filter eliminates small areas, such as noise, thus extracting building objects. To evaluate the proposed method, we applied this and three other methods to five sites in different environments. The experiment showed that the proposed method leads to a notable increase in accuracy over three other methods when compared with the in situ reference data.     

Self‐supervised learning to visually detect terrain surfaces for autonomous robots operating in forested terrain

Autonomous robotic navigation in forested environments is difficult because of the highly variable appearance and geometric properties of the terrain. In most navigation systems, researchers assume a priori knowledge of the terrain appearance properties, geometric properties, or both. In forest environments, vegetation such as trees, shrubs, and bushes has appearance and geometric properties that vary with change of seasons, vegetation age, and vegetation species. In addition, in forested environments the terrain surface is often rough, sloped, and/or covered with a surface layer of grass, vegetation, or snow. The complexity of the forest environment presents difficult challenges for autonomous navigation systems. In this paper, a self‐supervised sensing approach is introduced that attempts to robustly identify a drivable terrain surface for robots operating in forested terrain. The sensing system employs both LIDAR and vision sensor data. There are three main stages in the system: feature learning, feature training, and terrain prediction. In the feature learning stage, 3D range points from LIDAR are analyzed to obtain an estimate of the ground surface location. In the feature training stage, the ground surface estimate is used to train a visual classifier to discriminate between ground and nonground regions of the image. In the prediction stage, the ground surface location can be estimated at high frequency solely from vision sensor data. © 2012 Wiley Periodicals, Inc.     

Detection and typification of linear structures for dynamic visualization of 3D city models

Cluttering is a fundamental problem in 3D city model visualization. In this paper, a novel method for removing cluttering by typification of linear building groups is proposed. This method works in static as well as dynamic visualization of 3D city models. The method starts by converting building models in higher Levels of Details (LoDs) into LoD1 with ground plan and height. Then the Minimum Spanning Tree (MST) is generated according to the distance between the building ground plans. Based on the MST, linear building groups are detected for typification. The typification level of a building group is determined by its distance to the viewpoint as well as its viewing angle. Next, the selected buildings are removed and the remaining ones are adjusted in each group separately. To preserve the building features and their spatial distribution, Attributed Relational Graph (ARG) and Nested Earth Mover’s Distance (NEMD) are used to evaluate the difference between the original building objects and the generalized ones. The experimental results indicate that our method can reduce the number of buildings while preserving the visual similarity of the urban areas.     

Plant detection and mapping for agricultural robots using a 3D LIDAR sensor

In this article, we discuss the advantages of MEMS based 3D LIDAR sensors over traditional approaches like vision or stereo vision in the domain of agricultural robotics and compare these kinds of sensors with typical 3D sensors used on mobile robots. Further, we present an application for such sensors. This application deals with the detection and segmentation of plants and ground, which is one important prerequisite to perform localization, mapping and navigation for autonomous agricultural robots. We show the discrimination of ground and plants as well as the mapping of the plants. Experiments conducted using the FX6 LIDAR by Nippon Signal were carried out in the simulation environment Gazebo, with artificial maize plants in the laboratory and on a small maize field. Our results show that the tested plants can be reliably detected and segmented from ground, despite the use of the low resolution FX6 sensor. Further, the plants can be localized with high accuracy.     

基于机载视频量测的3维城市建模

3维城市模型的快速获取及更新是近十年来计算机视觉及数字摄影测量领域研究的热点。从实用、经济的角度出发，提出了集成城市数字地图、LIDAR data以及机载视频序列影像多数据源，基于数字摄影测量理论的半自动获取3维城市模型的解决办法，并在3维导航的数据生产实践中进行了验证，取得较好的生产效率及效果。     

Use of lidar-derived NDTI and intensity for rule-based object-oriented extraction of building footprints

Buildings play an essential role in urban intra-construction, planning, and climate. The precise knowledge of building footprints not only serves as a primary source for interpreting complex urban characteristics, but also provides regional planners with more realistic and multidimensional scenarios for urban management. The recently developed airborne light detection and ranging (lidar) technology provides a very promising alternative for building-footprint measurement. In this study, lidar intensity data, a normalized digital surface model (nDSM) of the first and last returns, and the normalized difference tree index (NDTI) derived from the two returns are used to extract building footprints using rule-based object-oriented classification. The study area is chosen in London, Ontario, based on the various types of buildings surrounded by trees. An integrated segmentation approach and a hierarchical rule-based classification strategy are proposed during the process. The results indicate that the proposed object-based classification is a very effective semi-automatic method for building-footprint extraction, with buildings and trees successfully separated. An overall accuracy of 94.0% and a commission error of 6.3% with a kappa value of 0.84 are achieved. Lidar-derived NDTI and intensity data are of great importance in object-based building extraction, and the kappa value of the proposed method is double that of the object-based method without NDTI or intensity.     

Area-wide roof plane segmentation in airborne LiDAR point clouds

Most algorithms performing segmentation of 3D point cloud data acquired by, e.g. Airborne Laser Scanning (ALS) systems are not suitable for large study areas because the huge amount of point cloud data cannot be processed in the computer’s main memory. In this study a new workflow for seamless automated roof plane detection from ALS data is presented and applied to a large study area. The design of the workflow allows area-wide segmentation of roof planes on common computer hardware but leaves the option open to be combined with distributed computing (e.g. cluster and grid environments). The workflow that is fully implemented in a Geographical Information System (GIS) uses the geometrical information of the 3D point cloud and involves four major steps: (i) The whole dataset is divided into several overlapping subareas, i.e. tiles. (ii) A raster based candidate region detection algorithm is performed for each tile that identifies potential areas containing buildings. (iii) The resulting building candidate regions of all tiles are merged and those areas overlapping one another from adjacent tiles are united to a single building area. (iv) Finally, three dimensional roof planes are extracted from the building candidate regions and each region is treated separately. The presented workflow reduces the data volume of the point cloud that has to be analyzed significantly and leads to the main advantage that seamless area-wide point cloud based segmentation can be performed without requiring a computationally intensive algorithm detecting and combining segments being part of several subareas (i.e. processing tiles). A reduction of 85% of the input data volume for point cloud segmentation in the presented study area could be achieved, which directly decreases computation time.