Non-ground Points Research Articles

Building Extraction from Lidar Data Using Statistical Methods

In this article, a straightforward, intuitive method for lidar data classification and building extraction, based on statistical analysis, is presented. The classification of the point cloud into ground and nonground is begun by individually testing each point within the point cloud using the statistical mean height. In this operation, various window sizes are specified, and the mean is obtained at each size. The points that are above the mean are saved and divided by the number of windows to obtain the proportion. Points are considered non-ground if their proportion is higher than the assigned threshold, and otherwise ground. An algorithm for classifying the obtained nonground point cloud into buildings and trees is also illustrated in this article. First the nonground points are labeled, then each label is tested individually. The process begins with segmenting each label. Then comes testing of whether each segment of points can be fitted within a specific plane. The label of the point cloud is considered a building if the number of segments considered as planes is larger than those considered as nonplanes; otherwise it is classified as a tree.

A Fast Progressive TIN Densification Filtering Algorithm for Airborne LiDAR Data Using Adjacent Surface Information

Point cloud filtering is a preliminary and essential step in various applications of airborne LiDAR (light detection and ranging) data, with progressive triangulated irregular network (TIN) densification (PTD) being one of the classic methods for filtering LiDAR point clouds. The PTD algorithm densifies ground points through iteration operation based on initial ground seed points. However, the poor performance in steeply sloped areas and time-consuming processing are serious drawbacks for PTD algorithms. In this paper, we propose a fast progressive TIN densification (FPTD) filtering algorithm for airborne LiDAR data using adjacent surface information. After carefully establishing parameters and removing outliers, our improved FPTD uses a sliding window to obtain significantly more initial ground seed points. And we modified some iterative determination criterion, including the definition of maximum relative elevation threshold and the introduction of signed computation, to eliminate avoidable non-ground points. Then adjacent surface information was utilized to iterate each point cloud block, which is the smallest unit that point cloud can be segmented. Additionally, the algorithm is easily run in a multi-threaded environment, further accelerating the filtering process to some extent. Experiments show that our proposed FPTD filtering algorithm is fast and robust. Compared to the PTD, the FPTD algorithm yields better error rates and kappa coefficients in 1/12 of the time required by the PTD.

LiDAR derived shack footprint for the City of Cape Town, South Africa

ABSTRACT Shack extraction is a growing application area for solving contemporary geographical complexities in developing countries. Traditional ground-based surveys that provided shack counts are being overtaken by the opportunities around rapid advances in spatial data collection. The ability to automate and report high accuracies against ground truth remains key to the complex nature of the digital shack extraction matrix. This study uses 8 cm aerial footage and laser scanning data to map informal settlement areas within built environments. The research design includes a set of experiments in defining the footprint of shacks obtained through profiling sampled shack/non-shack areas. Average shack heights, behaviour of unclassified points, number of non-ground points, scan texture and intensity variations were investigated. A five-parameter signature was applied to a pit-free normalized digital surface model (NDSM) and as expected on both test and validation, proved suitable for distinct shacks identification. This approach reported a 95% large settlement detection within a 1-metre-wide boundary position tolerance, coupled with a few false positives in isolated cases of multi-storey, sheds and also complex shacks. The results are proposed for inclusion in city-wide urban planning frameworks that can also be tweaked to include social and environmental parameters.

Continuous-Time Laser Frames Associating and Mapping via Multilayer Optimization.

To achieve the ability of associating continuous-time laser frames is of vital importance but challenging for hand-held or backpack simultaneous localization and mapping (SLAM). In this study, the complex associating and mapping problem is investigated and modeled as a multilayer optimization problem to realize low drift localization and point cloud map reconstruction without the assistance of the GNSS/INS navigation systems. 3D point clouds are aligned among consecutive frames, submaps, and closed-loop frames using the normal distributions transform (NDT) algorithm and the iterative closest point (ICP) algorithm. The ground points are extracted automatically, while the non-ground points are automatically segmented to different point clusters with some noise point clusters omitted before 3D point clouds are aligned. Through the three levels of interframe association, submap matching and closed-loop optimization, the continuous-time laser frames can be accurately associated to guarantee the consistency of 3D point cloud map. Finally, the proposed method was evaluated in different scenarios, the experimental results showed that the proposed method could not only achieve accurate mapping even in the complex scenes, but also successfully handle sparse laser frames well, which is critical for the scanners such as the new Velodyne VLP-16 scanner’s performance.

Filtering airborne LiDAR point clouds based on a scale-irrelevant and terrain-adaptive approach

Separating ground from non-ground points is a challenging and essential task before the applications of airborne Light Detection And Ranging (LiDAR) data. The classical filters generally show good results on simple landscapes, but suffer from large filtering errors on complex landscapes with steep slopes and terrain discontinuities. To produce more satisfactory results over these landscapes, a scale-irrelevant and terrain-adaptive interpolation-based filter is presented in this paper. The contributions of the proposed method include a 1D spline-based algorithm for the collection of evenly distributed ground seeds as many as possible, a scale-irrelevant interpolation for estimating the heights of unclassified points and a terrain-adaptive elevation threshold to adapt to various terrain characteristics. The performance of the proposed method was first evaluated on the International Society Photogrammetry and Remote Sensing (ISPRS) benchmark dataset. Results show that the proposed method with the average total error of 2.70% and kappa coefficient of 90.84% outperforms the existing filtering algorithms developed in recent decade (2010–2020). The performance of the proposed method was further assessed on four high-density airborne LiDAR point clouds located in urban and forested sites and compared with four state-of-the-art filters including progressive morphological filter (PMF), cloth simulation filter (CSF), progressive TIN densification (PTD) and multiresolution hierarchical filter (MHF). Results demonstrate that the proposed method is averagely more accurate than the well-known filters in terms of total error and kappa coefficient, and much faster than PTD and MHF. Moreover, the proposed method produces more satisfactory DEMs than the classical methods.

A mean shift segmentation morphological filter for airborne LiDAR DTM extraction under forest canopy

In recent years, many airborne point clouds filtering methods have been developed. However, it is still challenging for distinguishing ground and non-ground points in forested areas due to the rugged terrains, dense vegetation canopy and low-level penetration of laser pulses. To derive satisfactory filtering results, this paper proposed a mean shift segmentation morphological filter. In this method, the mean shift segmentation is used for acquiring object primitives to determine filtering window sizes automatically. The point clouds detrending is proposed for improving the adaptability towards sloped terrains. A point cloud shifting in x and y directions technique is developed to acquire more ground seeds for generating a more accurate trending surface. Finally, the filtered ground points by the progressive morphological filter are recovered by adopting the surface-based filtering strategy. The proposed method is tested and validated using 14 samples with different forested environments. Experimental results show that the proposed method can achieve the average total error of 1.11%. The kappa coefficients of all these 14 samples are larger than 90% and the average kappa coefficient is 96.43%. The average root mean square error (RMSE) of the proposed method is 0.63. All these indicators are the best when compared to some other famous filtering methods.

A METHOD FOR EXTRACTING SUBSTATION EQUIPMENT BASED ON UAV LASER SCANNING POINT CLOUDS

Abstract. Smart grid construction puts higher demands on the construction of 3D models of substations. However, duo to the complex and diverse structures of substation facilities, it is still a challenge to extract the fine three-dimensional structure of the substation facilities from the massive laser point clouds. To solve this problem, this paper proposes a method for extracting substation equipment from laser scanning point clouds. Firstly, in order to improve the processing efficiency and reduce the noises, the regular voxel grid sampling method is used to down-sample the input point cloud. Furthermore, the multi-scale morphological filtering algorithm is used to segment the point cloud into ground points and non-ground points. Based on the non-ground point cloud data, the substation region is extracted using plane detection in point clouds. Then, for the filtered substation point cloud data, a three-dimensional polygon prism segmentation algorithm based on point dimension feature is proposed to extract the substation equipment. Finally, the substation LiDAR point cloud data collected by the UAV laser scanning system is used to verify the algorithm, and the qualitative and quantitative comparison analysis between the detected results and the manually extracted results are carried out. The experimental results show that the proposed method can accurately extract the substation equipment structure from the laser point cloud data. The results are consistent with the manually extracted results, which demonstrate the great potential of the proposed method in substation extraction and power system 3D modelling applications.

An Airborne LiDAR Building-Extraction Method Based on the Naive Bayes–RANSAC Method for Proportional Segmentation of Quantitative Features

The study aims to address the multiple pseudo-planes and low efficiency of random sample consensus (RANSAC) while extracting building planes from airborne light detection and ranging (LiDAR) data. A Naive Bayes–RANSAC method is proposed for the proportional segmentation of quantitative features. First, the point cloud is divided into ground and non-ground points using the cloth simulation filtering (CSF) algorithm. RANSAC is used to extract the non-ground point directly. Accordingly, several planes are obtained as the original building roofs. The differences in the density and echo features between the pseudo-plane and the training samples’ building plane are then analyzed. The percentage of the points whose densities are greater than the threshold, determined by the densities of the building edges, is calculated within each plane. Similarly, the percentage of the points whose echo numbers are higher than one is calculated within each plane. The two percentages calculated above are used as the classification basis of Naive Bayes. Finally, the building roofs can be extracted with the Naive Bayes classifier. This method can extract building roofs from LiDAR point clouds without external data. Two experiments are conducted to reveal the method’s practicality and reliability. The results demonstrate completeness of 89.0% and correctness of 94.0% at the per-area level for the first experiment and 90.7% and 91.7% for the second experiment. Simultaneously, the second experiment exhibits superior results compared with other methods under the same conditions.

Coarse-to-Fine Segmentation on LiDAR Point Clouds in Spherical Coordinate and Beyond

Active sensors such as LiDARs (light detection and ranging) are popular in autonomous driving systems for perception and localization. Existing perception approaches process the rich 3D LiDAR point clouds for object detection, tracking and recognition. These methods generally require an initial segmentation procedure containing two steps: (1) filter points as ground and non-ground points, and (2) cluster the non-ground points into objects. Leveraging a range image created in Spherical coordinates, this paper proposes a field-tested coarse-to-fine 3D point cloud segmentation framework to achieve both speed and accuracy. Under this framework, a basic version and an advanced version of segmentation algorithms are presented. In the basic version, we demonstrate how a coarse-to-fine scheme is applied in a range image for ground filtering and object clustering. In the advanced version, we move forward to reduce the processing time and correct the motion distortion by directly dealing with the data packets instead of the range image. Tests in the well-known KITTI dataset and field experiments in public roads have shown that the method significantly improves the speed of 3D point cloud segmentation whilst maintains good accuracy.

Hierarchical Instance Recognition of Individual Roadside Trees in Environmentally Complex Urban Areas from UAV Laser Scanning Point Clouds

Individual tree segmentation is essential for many applications in city management and urban ecology. Light Detection and Ranging (LiDAR) system acquires accurate point clouds in a fast and environmentally-friendly manner, which enables single tree detection. However, the large number of object categories and occlusion from nearby objects in complex environment pose great challenges in urban tree inventory, resulting in omission or commission errors. Therefore, this paper addresses these challenges and increases the accuracy of individual tree segmentation by proposing an automated method for instance recognition urban roadside trees. The proposed algorithm was implemented of unmanned aerial vehicles laser scanning (UAV-LS) data. First, an improved filtering algorithm was developed to identify ground and non-ground points. Second, we extracted tree-like objects via labeling on non-ground points using a deep learning model with a few smaller modifications. Unlike only concentrating on the global features in previous method, the proposed method revises a pointwise semantic learning network to capture both the global and local information at multiple scales, significantly avoiding the information loss in local neighborhoods and reducing useless convolutional computations. Afterwards, the semantic representation is fed into a graph-structured optimization model, which obtains globally optimal classification results by constructing a weighted indirect graph and solving the optimization problem with graph-cuts. The segmented tree points were extracted and consolidated through a series of operations, and they were finally recognized by combining graph embedding learning with a structure-aware loss function and a supervoxel-based normalized cut segmentation method. Experimental results on two public datasets demonstrated that our framework achieved better performance in terms of classification accuracy and recognition ratio of tree.

Building Extraction from Airborne LiDAR Data Based on Min-Cut and Improved Post-Processing

Building extraction from LiDAR data has been an active research area, but it is difficult to discriminate between buildings and vegetation in complex urban scenes. A building extraction method from LiDAR data based on minimum cut (min-cut) and improved post-processing is proposed. To discriminate building points on the intersecting roof planes from vegetation, a point feature based on the variance of normal vectors estimated via low-rank subspace clustering (LRSC) technique is proposed, and non-ground points are separated into two subsets based on min-cut after filtering. Then, the results of building extraction are refined via improved post-processing using restricted region growing and the constraints of height, the maximum intersection angle and consistency. The maximum intersection angle constraint removes large non-building point clusters with narrow width, such as greenbelt along streets. Contextual information and consistency constraint are both used to eliminate inhomogeneity. Experiments of seven datasets, including five datasets provided by the International Society for Photogrammetry and Remote Sensing (ISPRS), one dataset with high-density point data and one dataset with dense buildings, verify that most buildings, even with curved roofs, are successfully extracted by the proposed method, with over 94.1% completeness and a minimum 89.8% correctness at the per-area level. In addition, the proposed point feature significantly outperforms the comparison alternative and is less sensitive to feature threshold in complex scenes. Hence, the extracted building points can be used in various applications.

A Self-Adaptive Morphological Filter without Consideration of Window Size for Airborne LiDAR Point Clouds

Light detection and ranging (LiDAR) has the capability of rapidly collecting dense and accurate three-dimensional geospatial information, and therefore it is widely applied in various fields of geospatial applications. The morphological filtering approaches can filter non-ground points effectively, which is crucial for many tasks such as land cover classification and digital elevation model generation. A series of different windows are generally in need for removing non-ground objects with different sizes. In order to avoid the limitation of choosing the filtering windows, we adopt the geodesic transformations of mathematical morphology for filtering LiDAR point clouds. This algorithm enhances the robustness and automation without consideration of how to choose different windows. Experimental results demonstrate that this filtering algorithm is capable of effectively preserving terrain details and filtering various non-ground objects.

SEMANTIC CLASSIFICATION OF SANDSTONE LANDSCAPE POINT CLOUD BASED ON NEIGHBOURHOOD FEATURES

Abstract. The technology of airborne laser scanning enables fast and accurate gathering spatial data containing also echoes from the terrain below the vegetation canopy that is beneficial for topographic mapping of wooded sandstone landscapes in Czechia, Poland, and Germany. The challengeable task is to determine the ground points in the point cloud because commonly used filtration methods do not successfully distinguish between vegetation and rock pillars and faces. In this paper, we replace filtration with classification approach using the features derived from characteristics of points within a neighbourhood of optimized sizes, such as eigenvalue-based features and echo ratio. Random Forest classifier is trained and tested on the manually labelled dataset with a density of almost 650 points/m2 from the Adršpach-Teplice Rocks. The overall accuracy reaches 87% but recall and precision of non-ground points are unsatisfactory. Misclassified non-ground points are located also within trees, thus we do not consider the result as suitable for DTM processing without further processing.

TERRAIN-ADAPTIVE GROUND FILTERING OF AIRBORNE LIDAR DATA BASED ON SALIENCY-AWARE THIN PLATE SPLINE

Abstract. Ground filtering separates the ground and non-ground points from point clouds, which is the essential process for DEM generation, semantic segmentation, model reconstruction and so forth. Considering the topologically complex terrain environments, the segmentation results are prone to be disturbed dealing with steep slopes, buildings, bridges, cliffs, etc. from Airborne LiDAR point clouds. In this paper, a saliency-aware Thin-Plate-Spline (SATPS) interpolation method is proposed including two steps: saliency division and adaptive regularized TPS interpolation with relative variance coefficient. Firstly, the point clouds are indexed in 2D grids and segments are clustered step probing toward 8-adjacent scanning directions. Then, the saliency of each grid is calculated according to the elevation variance of adjacent segments towards each scanning direction. Subsequently, grids of high ground saliency are considered as candidates for seed point selection and then clustered by region growing. The TPS surface is interpolated for each cluster loosely fitting to the seed points involving an adaptive relative variance coefficient which is according to ground saliency and elevation deviation. And finally, the ground points are extracted around the TPS surface. Experimental results indicate that the proposed SATPS algorithm achieves better Type 1 accuracy and total accuracy than the state-of-the-art algorithms in scenes with complex terrain structures, which is practical to generate DEM products.

Urban vehicle extraction from aerial laser scanning point cloud data

ABSTRACT A vehicle extraction method is proposed in this paper to extract vehicles in urban areas more accurately from airborne point clouds. First, the ground points are separated from the non-ground points, and a potential vehicle-occupied area (PVOA) is then extracted from the ground point cloud. A PVOA-based non-ground point cloud segmentation method is proposed in this work, and a gap-based method is put forward to re-cluster the segment, which may include multiple vehicles. The non-ground point cloud is clustered into a series of one-vehicle segments and empty segments. Following this, a shape-based vehicle recognition method is presented that can judge whether or not a given segment is a vehicle using a dynamic time warping similarity measurement. In addition to judging whether or not a segment is a vehicle, the category of each vehicle can also be determined. To a significant extent, our PVOA-based non-ground point cloud segmentation method can avoid the difficulties of over- and under-segmentation that arise in current mainstream methods of object-based vehicle extraction, and can also avoid incorrect segmentation in case of vehicles parked close together. Our shape-based vehicle recognition method can exclude non-vehicle objects, especially those with sizes similar to those of vehicles. This method is more effective than current algorithms based on normal geometric features such as area and rectangularity. Using four datasets of typical urban scenarios, the performance of the new algorithm is tested and compared with that of the OBPCA and DT algorithm. The experimental results show that the correctness, completeness, and quality of the new algorithm are 96.7%, 91.1%, and 93.8%, higher than that of the OBPCA and DT algorithm.

Delineating planner surfaces from correlation-based DEMS

Planner surfaces play an important role in several mapping and planning applications in urban areas. Automated algorithms to extract such surfaces are essential since they reduce the time and cost when compared to editing these DEMs manually. These surfaces could be constructed from either correlation-based DEMs or LIDAR point clouds. The advantages of the first over the second make it more appealing in generating 3D planer surfaces. In this paper we outline an automated algorithm to delineate 3D surfaces in DEMs compiled from a set of high resolution digital aerial photographs. Each cell in the DEM is assigned three attributes representing: height from bare ground, local statistics of neighboring elevations, and homogeneity of pixel intensities in corresponding aerial photos. These attributes are used to classify DEM points to ground and non-ground points using a feedforward back-propagation neural network. Candidate non-ground points are further segmented into different surfaces based on their tendency to lie in a plane. The 3D parameters of roof planes are then estimated using a robust estimator and regression analyses. DEM points contiguous to the roof patches are augmented if they pass an intensity compatibility check. Results showed an average increase in the precision of the DEMs’ heights for roof posts from 48 cm to 15 cm.

Coherent Markov Random Field-Based Unreliable DSM Areas Segmentation and Hierarchical Adaptive Surface Fitting for InSAR DEM Reconstruction.

A digital elevation model (DEM) can be obtained by removing ground objects, such as buildings, in a digital surface model (DSM) generated by the interferometric synthetic aperture radar (InSAR) system. However, the imaging mechanism will cause unreliable DSM areas such as layover and shadow in the building areas, which seriously affect the elevation accuracy of the DEM generated from the DSM. Driven by above problem, this paper proposed a novel DEM reconstruction method. Coherent Markov random field (CMRF) was first used to segment unreliable DSM areas. With the help of coherence coefficients and residue information provided by the InSAR system, CMRF has shown better segmentation results than traditional traditional Markov random field (MRF) which only use fixed parameters to determine the neighborhood energy. Based on segmentation results, the hierarchical adaptive surface fitting (with gradually changing the grid size and adaptive threshold) was set up to locate the non-ground points. The adaptive surface fitting was superior to the surface fitting-based method with fixed grid size and threshold of height differences. Finally, interpolation based on an inverse distance weighted (IDW) algorithm combining coherence coefficient was performed to reconstruct a DEM. The airborne InSAR data from the Institute of Electronics, Chinese Academy of Sciences has been researched, and the experimental results show that our method can filter out buildings and identify natural terrain effectively while retaining most of the terrain features.

RESEARCH ON CONSTRUCTING DEM WITH POINT CLOUD FILTERING ALGORITHM CONSIDERING SPECIAL TERRAIN

Abstract. With the development of airborne LiDAR, the use of LiDAR point cloud to construct DEM model is a hot topic in recent years. For the characteristics of time cloud filtering and poor validity, and the efficiency of non-ground point filtering is not high, the filtered point cloud has problems such as errors and leaks. This paper proposes a method of constructing DEM based on the point cloud filtering algorithm of airborne Lidar point cloud data considering special terrain. The experiment proves that the algorithm of this paper is effective for establishing DEM model, and the quality of DEM model is good.

LIDAR DATA FILTERING BASED ON THE IMPROVED WINDOW SIZE OF PROGRESSIVE MATHEMATICAL MORPHOLOGY

Abstract. Filtering is one of the core post-processing steps of airborne LiDAR point cloud data. It is difficult for traditional mathematical morphology filtering algorithms to preserve sudden terrain features, especially when using larger filtering windows. In this paper, an improved progressive mathematical morphology filtering algorithm is proposed to solve the problem which is difficult to filter out a large area of non-ground points effectively and causes omission filtering on prominent topographic features. First the elevation information of point cloud data is meshed, and then the opening operation (erosion and dilation) is performed. By improving the mathematical formula of window size, the window size and the corresponding elevation difference threshold are iterated continuously. Within each corresponding filtering window, objects that are larger than the size of the structural element window are retained, and objects smaller than the size of the structural element window are filtered. Fourteen samples provided by ISPRS committee were selected to test the performance of the proposed method. Experimental results show that the improved method can effectively filter out most of the non-ground points, and this method can achieve great results not only in urban flat areas, but also in the mountains. Compared with the traditional filtering methods, the filter performance of the new method proposed in this paper has been greatly improved. The method in this paper obtains the lower errors and retains the complex topographic features.

POWER LINE EXTRACTION AND ANALYSIS BASED ON LIDAR

Abstract. The traditional electrical power line inspection method has the disadvantages of high labor intensity, low efficiency and long cycle of re-inspection. Airborne LiDAR can quickly obtain the high-precision three-dimensional spatial information of transmission line, and the data which collected by it can make it possible to accurately detect the dangerous points.It is proposed to use the grid method to divide the data into multiple regions for the elevation histogram statistical method to obtain the power line point cloud at the complex mountainous terrain. In the non-ground point data, part of the vegetation point cloud is separated according to the point cloud dimension feature, and then the power line point and the pole point are distinguished according to the density characteristics of the point cloud so as to realize the point cloud classification of the transmission line corridor. On this basis, the power line safety distance detection is carried out on the power line points and vegetation points extracted by the classification, and the early warning analysis of the dangerous points of the transmission line tree barrier is completed. The experimental results show that the method can classify the acquired power line corridor point cloud and extract the complete power line, which effectively eliminates the hidden dangers and has certain practical significance.