Ground Point Cloud Research Articles

Quantifying the Effect of LiDAR Data Density on DEM Quality


 
 
 
 LiDAR sensors capture three-dimensional point clouds with high accuracy and density; since they are regularly obtained, interpolation methods are required to generate a regular grid. Given the large size of its files, processing becomes a challenge for researchers with not very powerful computer stations. This work aims to balance the sampling density and the volume of data, preserving the sensitivity of representation of complex topographic shapes as a function of three surface descriptors: slope, curvature, and roughness. This study explores the effect of the density of LiDAR data on the accuracy of the Digital Elevation Model (DEM), using a ground point cloud of 32 million measurements obtained from a LiDAR flight over a complex topographic area of 156 ha. Digital elevation models with different relative densities to the total point dataset were produced (100, 75, 50, 25, 10, and 1 % and at different grid sizes 23, 27, 33, 46, 73, and 230cm). Accuracy was evaluated using the Inverse Distance Weighted and Kriging interpolation algorithms, obtaining 72 surfaces from which their error statistics were calculated: root mean square error, mean absolute error, mean square error, and prediction effectiveness index; these were used to evaluate the quality of the results in contrast with validation data corresponding to 10 % of the original sample. The results indicated that Kriging was the most efficient algorithm, reducing data to 1 % without statistically significant differences with the original dataset, and curvature was the morphometric parameter with the most significant negative impact on interpolation accuracy.
 
 
 

Obstacle Detection Based on 3D Lidar Euclidean Clustering

Environment perception is the basis of unmanned driving and obstacle detection is an important research area of environment perception technology. In order to quickly and accurately identify the obstacles in the direction of vehicle travel and obtain their location information, combined with the PCL (Point Cloud Library) function module, this paper designed a euclidean distance based Point Cloud clustering obstacle detection algorithm. Environmental information was obtained by 3D lidar, and ROI extraction, voxel filtering sampling, outlier point filtering, ground point cloud segmentation, Euclide clustering and other processing were carried out to achieve a complete PCL based 3D point cloud obstacle detection method. The experimental results show that the vehicle can effectively identify the obstacles in the area and obtain their location information.

Pole-Like Objects Segmentation and Multiscale Classification-Based Fusion from Mobile Point Clouds in Road Scenes

Real-time acquisition and intelligent classification of pole-like street-object point clouds are of great significance in the construction of smart cities. Efficient point cloud processing technology in road scenes can accelerate the development of intelligent transportation and promote the development of high-precision maps. However, available algorithms have the problems of incomplete extraction and the low recognition accuracy of pole-like objects. In this paper, we propose a segmentation method of pole-like objects under geometric structural constraints. As for classification, we fused the classification results at different scales with each other. First, the point cloud data excluding ground point clouds were divided into voxels, and the rod-shaped parts of the pole-like objects were extracted according to the vertical continuity. Second, the regional growth based on the voxel was carried out based on the rod part to retain the non-rod part of the pole-like objects. A one-way double coding strategy was adopted to preserve the details. For spatial overlapping entities, we used multi-rule supervoxels to divide them. Finally, the random forest model was used to classify the pole-like objects based on local- and global-scale features and to fuse the double classification results under the different scales in order to obtain the final result. Experiments showed that the proposed method can effectively extract the pole-like objects of the point clouds in the road scenes, indicating that the method can achieve high-precision classification and identification in the lightweight data. Our method can also bring processing inspiration for large data.

Obstacle detection and recognition in farmland based on fusion point cloud data

Obstacle detection and recognition in the farmland environment is of great significance to unmanned agricultural machinery navigation technology. In this study, a tractor platform based on 3D/2D LiDAR and GNSS/AHRS was built to acquire fusion point cloud data. A complete data processing flow is proposed, including fusion point cloud data acquisition, obstacle detection, and obstacle recognition. The fusing point cloud data acquisition method realized the time synchronization between multiple sensors and the space registration of point cloud at different coordinate systems. The obstacle detection method removed ground, sparse, and ego platform points based on RANSAC and crop-box filtering. Then, a Euclidean clustering method based on the platform width was used for obstacle clustering. The obstacle recognition method established a box model based on PCA for each cluster and extracted its geometric feature information. Next, a MCB classification method is proposed to distinguish false-positive, non-interest, and trackable obstacles (e.g., tractor and pedestrian). To evaluate the results of data collection and processing, a series of experiments was designed and implemented. The average absolute deviation of the fusion point cloud was 0.015 m, and the average rate of lost was 1.24%. The proportion of residual ground points in the ground point cloud was less than 0.012%. The accuracy, precision, recall, and F1-score exceeded 80%. Therefore, the proposed method could meet the operation requirements in the farmland environment and provide highly precise and stable detection and recognition results.

Ground Segmentation Algorithm of Lidar Point Cloud Based on Ray-Ransac

Aiming at the problems of poor segmentation effect, low efficiency and poor robustness of the Ransac ground segmentation algorithm, this paper proposes a radar segmentation algorithm based on Ray-Ransac. This algorithm combines the structural characteristics of three-dimensional lidar and uses ray segmentation to generate the original seed point set. The random sampling of Ransac algorithm is limited to the original seed point set, which reduces the probability that Ransac algorithm extracts outliers and reduces the calculation. The Ransac algorithm is used to modify the ground model parameters so that the algorithm can adapt to the undulating roads. The standard deviation of the distance from the point to the plane model is used as the distance threshold, and the allowable error range of the actual point cloud data is considered to effectively eliminate the abnormal points and error points. The algorithm was tested on the simulation platform and the test vehicle. The experimental results show that the lidar point cloud ground segmentation algorithm proposed in this paper takes an average of 5.784 milliseconds per frame, which has fast speed and good precision. It can adapt to uneven road surface and has high robustness.

A Fast Point Cloud Ground Segmentation Approach Based on Coarse-To-Fine Markov Random Field

Ground segmentation is an important preprocessing task for autonomous vehicles (AVs) with 3D LiDARs. However, the existing ground segmentation methods are very difficult to balance accuracy and computational complexity. This paper proposes a fast point cloud ground segmentation approach based on a coarse-to-fine Markov random field (MRF) method. The method uses the coarse segmentation result of an improved local feature extraction algorithm instead of prior knowledge to initialize an MRF model. It provides an initial value for the fine segmentation and dramatically reduces the computational complexity. The graph cut method is then used to minimize the proposed model to achieve fine segmentation. Experiments on two public datasets and field tests show that our approach is more accurate than both methods based on features and MRF and faster than graph-based methods. It can process Velodyne HDL-64E data frames in real-time (24.86 ms, on average) with only one thread of the I7-8700 CPU. Compared with methods based on deep learning, it has better environmental adaptability.

Automatic extraction of trees by using multiple return properties of the lidar point cloud

Airborne laser scanning has been a valuable tool for forestry applications since it began to be used commercially. Thanks to the high 3D resolution provided by the Light Detection and Ranging (LiDAR) point cloud, it has provided great convenience in complex 3D modeling processes needed for forestry applications such as forest inventory, forest management, determination of carbon stocks and the characterization of biodiversity. LiDAR data provides a new dimension in forestry applications with its high 3D resolution and multiple return characteristics. The extraction of woodland areas from the LiDAR point cloud has great importance for automating the determination of tree heights, species and stand frequency which will be used for generating canopy height models (CHM). In this study, woodland areas in the urban scene were automatically extracted by using the multiple return properties of the LiDAR point cloud. The proposed approach consists of three major steps namely pre-processing, parameter calculation and k-d tree search for trees which were implemented in MATLAB. In the first step, multiple return points have been identified from the LiDAR point cloud, which will be then used to determine possible tree locations. Then, by using Density-Based Spatial Clustering of Applications with Noise (DBSCAN) algorithm, neighborhood relations among the multi return points which were extracted from the initial point cloud data, were formed and a rule-based filter was applied by taking advantage of neighborhood relations. In addition, the initial point cloud was filtered with the Cloth Simulation Filtering (CSF) algorithm to separate ground and non-ground points where non-ground points used to extract trees. In the second step, non-vegetation points were removed by applying a threshold based on the change of curvature and planarity parameters, which are derived from the filtered non–ground point cloud. In the last step, in order to extract trees, a k-d tree structure was created from the filtered non-ground points to find nearest neighbors of each multi return point within a given diameter in the k-d tree structure. In order to evaluate the accuracy of the approach, the extracted boundaries were compared with the manually digitized woodland boundaries from the true orthophoto of the study area using correctness, completeness and quality metrics.

Separation of Wood and Foliage for Trees From Ground Point Clouds Using a Novel Least-Cost Path Model

Nowadays, laser scanning technology has provided an effective andnondestructive approach to reveal the forest's developmental process and physiological properties. For the purpose of obtaining the 3-D spatial structure and skeleton of trees, this article addresses the separation of wood and foliage from the forest using two phases. The first global phase develops a pointwise supervised learning framework to classify forest point clouds. In order to improve the classification accuracy, we design new features for the learning process, which supplements the current geometric features in terms of the topological information. The second local phase designs a new least-cost path model to further separate wood and foliage points. The separation of branch points is formulated as an energy function and optimized by the dynamic programming technique. Experiments on different plots show that points from stems and branches are detected as wood points completely and correctly. The achieved average completeness, correctness, and F <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">1</sub> score of the wood and foliage separation are 91.25%, 90.34%, and 0.91, respectively, which is promising to the phenotyping study related to the organism's physical form and structure.

Canopy Extraction and Height Estimation of Trees in a Shelter Forest Based on Fusion of an Airborne Multispectral Image and Photogrammetric Point Cloud

To reduce data acquisition cost, this study proposed a novel method of individual tree height estimation and canopy extraction based on fusion of an airborne multispectral image and photogrammetric point cloud. A fixed‐wing drone was deployed to acquire the true color and multispectral images of a shelter forest. The Structure‐from‐Motion (SfM) algorithm was used to reconstruct the 3D point cloud of the canopy. The 3D point cloud was filtered to acquire the ground point cloud and then interpolated to a Digital Elevation Model (DEM) using the Radial Basis Function Neural Network (RBFNN). The DEM was subtracted from the Digital Surface Model (DSM) generated from the original point cloud to get the canopy height model (CHM). The CHM was processed for the crown extraction using local maximum filters and watershed segmentation. Then, object‐oriented methods were employed in the combination of 12 bands and CHM for image segmentation. To extract the tree crown, the Support Vector Machine (SVM) algorithm was used. The result of the object‐oriented method was vectorized and superimposed on the CHM to estimate the tree height. Experimental results demonstrated that it is efficient to employ point cloud and the proposed approach has great potential in the tree height estimation. The proposed object‐oriented method based on fusion of a multispectral image and CHM effectively reduced the oversegmentation and undersegmentation, with an increase in the F‐score by 0.12–0.17. Our findings provided a reference for the health and change monitoring of shelter forests as well.

Research on Automatic Denoising of LIDAR Point Cloud Data for Substation Equipment Based on Spatial Grid Density

Aiming at the shortcomings of the existing 3D point cloud data automatic extraction methods of substation equipment, which are highly dependent on big data algorithms and low efficiency, this paper proposes a 3D LIDAR point cloud data segmentation method and process based on the multidimensional subspace grid density difference. The proposed method is based on eliminating the flying spots of 3D point cloud data, and is divided into equipment point cloud data and ground point cloud data based on point cloud data characteristics for 3D real-world modeling and accurate positioning of the model; Among them, the equipment point cloud data uses a multi-dimensional density difference segmentation method. The long-distance terrain is divided in the XOY and YOZ planes, and converted into a combination of multiple small-scale scale spaces. Effective segmentation, so that automatic extraction of substation equipment can be realized; The ground point cloud data uses a single-dimensional density difference segmentation method to dilute the ground point cloud data to obtain clear positioning points. The feasibility verification results of cloud data of a UHV substation show that the proposed method can effectively suppress the noise interference of interference points, realize accurate extraction and location of substation equipment, and the algorithm has high efficiency and strong engineering application.

Application of Visible Image and LiDAR Point Cloud Fusion Technology in Distribution Network Tree Barrier Inspection

Aiming at the problems of poor visual effect and low accuracy of single use of LiDAR or visible light camera for tree barriers inspection in distribution corridors, the LiDAR point cloud data and visible light image data are obtained simultaneously through UAV carrying integrated system. First, the LiDAR point cloud data are de-noised, filtered and classified, and the ground and non-ground laser point clouds are separated. Then, the laser point cloud data and visible image data are set up in the same coordinate system by coordinate conversion. Then, the spectral information of visible image is assigned to the corresponding point cloud, and the 3D real scene image of point cloud is reproduced to realize the function of identifying and analyzing the hidden trouble of distribution corridor tree barrier. It greatly improves the accuracy and efficiency of tree barriers hidden trouble inspection, and the visual effect is intuitive.

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.

Real-Time Mine Road Boundary Detection and Tracking for Autonomous Truck.

Road boundary detection is an important part of the perception of the autonomous driving. It is difficult to detect road boundaries of unstructured roads because there are no curbs. There are no clear boundaries on mine roads to distinguish areas within the road boundary line and areas outside the road boundary line. This paper proposes a real-time road boundary detection and tracking method by a 3D-LIDAR sensor. The road boundary points are extracted from the detected elevated point clouds above the ground point cloud according to the spatial distance characteristics and the angular features. Road tracking is to predict and update the boundary point information in real-time, in order to prevent false and missed detection. The experimental verification of mine road data shows the accuracy and robustness of the proposed algorithm.

结合统计滤波与密度聚类的矿山地面点云提取算法

结合统计滤波与密度聚类的矿山地面点云提取算法

Vehicle pose estimation algorithm for parking automated guided vehicle

Parking automated guided vehicle is more and more widely used for efficient automatic parking and one of the tough challenges for parking automated guided vehicle is the problem of vehicle pose estimation. The traditional algorithms rely on the profile information of vehicle body and sensors are required to be mounted at the top of the vehicle. However, the sensors are always mounted at a lower place because the height of a parking automated guided vehicle is always beyond 0.2mm, where we can only get the vehicle wheel information and limited vehicle body information. In this article, a novel method is given based on the symmetry of wheel point clouds collected by 3-D lidar. Firstly, we combine cell-based method with support vector machine classifier to segment ground point clouds. Secondly, wheel point clouds are segmented from obstacle point clouds and their symmetry are corrected by iterative closest point algorithm. Then, we estimate the vehicle pose by the symmetry plane of wheel point clouds. Finally, we compare our method with registration method that combines sample consensus initial alignment algorithm and iterative closest point algorithm. The experiments have been carried out.

Extracting Diameter at Breast Height with a Handheld Mobile LiDAR System in an Outdoor Environment.

Mobile laser scanning (MLS) is widely used in the mapping of forest environments. It has become important for extracting the parameters of forest trees using the generated environmental map. In this study, a three-dimensional point cloud map of a forest area was generated by using the Velodyne VLP-16 LiDAR system, so as to extract the diameter at breast height (DBH) of individual trees. The Velodyne VLP-16 LiDAR system and inertial measurement units (IMU) were used to construct a mobile measurement platform for generating 3D point cloud maps for forest areas. The 3D point cloud map in the forest area was processed offline, and the ground point cloud was removed by the random sample consensus (RANSAC) algorithm. The trees in the experimental area were segmented by the European clustering algorithm, and the DBH component of the tree point cloud was extracted and projected onto a 2D plane, fitting the DBH of the trees using the RANSAC algorithm in the plane. A three-dimensional point cloud map of 71 trees was generated in the experimental area, and estimated the DBH. The mean and variance of the absolute error were 0.43 cm and 0.50, respectively. The relative error of the whole was 2.27%, the corresponding variance was 15.09, and the root mean square error (RMSE) was 0.70 cm. The experimental results were good and met the requirements of forestry mapping, and the application value and significance were presented.

A SIFT-Based DEM Extraction Approach Using GEOEYE-1 Satellite Stereo Pairs.

A module for Very High Resolution (VHR) satellite stereo-pair imagery processing and Digital Elevation Model (DEM) extraction is presented. A large file size of VHR satellite imagery is handled using the parallel processing of cascading image tiles. The Scale-Invariant Feature Transform (SIFT) algorithm detects potentially tentative feature matches, and the resulting feature pairs are filtered using a variable distance threshold RANdom SAmple Consensus (RANSAC) algorithm. Finally, point cloud ground coordinates for DEM generation are extracted from the homologous pairs. The criteria of average point spacing irregularity is introduced to assess the effective resolution of the produced DEMs. The module is tested with a 0.5 m × 0.5 m Geoeye-1 stereo pair over the island of Crete, Greece. Sensitivity analysis determines the optimum module parameterization. The resulting 1.5-m DEM has superior detail over reference DEMs, and results in a Root Mean Square Error (RMSE) of about 1 m compared to ground truth measurements.

Marker-free coregistration of UAV and backpack LiDAR point clouds in forested areas

Unmanned aerial vehicle Laser Scanning (ULS) and Backpack Laser Scanning (BLS) are two emerging mobile mapping technologies applicable for monitoring forested environments in unprecedented detail from complementary perspectives. Although ground-based backpack techniques provide detailed information about the forest understory and terrain, the measured point clouds based on SLAM techniques are stitched together gradually and normally expressed in a less-accurate arbitrary coordinate system. Conversely, ULS point clouds are acquired from above and usually georeferenced, yet the point density and penetrability near the ground may still suffer from dense overstory despite the low attitude operation. Coregistering the ground and aerial point clouds in the ULS coordinate system therefore provides a method for fusing understory and overstory information at single tree level without the time consuming procedure of applying ground control points. Since the ULS and BLS acquisition viewpoints differ greatly, standard coregistration methods requiring 3D point-level correspondences are likely to fail. This paper presents an object-level coregistration approach which instead operates on two sets of tree positions, with the goal of finding the optimal 3D transformation (consisting of rotation, translation and scaling) between the respective coordinate systems. The entire task is decomposed into separate problems of computing the common Z axis, estimating the scale, and 2D coregistration. In contrast to existing methods, our approach does not require additional information such as tree diameters or heights. We evaluated our method on real test plots involving diverse stem densities and tree species situated in forest farm of the eastern coastal region of Jiangsu, China. The tree positions for ground and aerial data were obtained respectively by cylinder fitting and tree segmentation. On 3 coniferous (dawn redwood) plots, 46–81% trees were matched with a distance below 50 cm, and mean position deviation of 27–36 cm. For 4 broadleaf (poplar) plots, no more than 50% trees were matched below a 1 m threshold and mean error of 54–67 cm, which can be attributed to the broadleaf trees’ more irregular shape and lack of a well defined tree top. Moreover, we show that the introduction of scaling into the transform can increase the matched tree count by up to 20 percentage points and decrease the mean matched distance by up to 13% compared to a strictly rigid transform.

Ground and aerial meta-data integration for localization and reconstruction: A review

Localization and reconstruction are two highly related research areas. Both of them have developed rapidly in recent years. Apparently, with the help of ground and aerial meta-data integration, the performance of both localization and reconstruction can go a step further. For localization, aerial meta-data provides a global reference, by which the ground query can achieve a cumulative error free absolute localization. As for reconstruction, a complete and detailed model can be reconstructed by integrating ground and aerial meta-data. Though with many advantages, the integration itself is non-trivial. It is difficult to obtain ground-to-aerial correspondences neither in 2D manner nor in 3D manner. That is because: (1) The differences between the ground and aerial images in viewpoint, scale, illumination, etc. are notable; (2) The discrepancies between the ground and aerial point clouds in terms of point density, accuracy, noise level, etc. are very large. To deal with these problems, lots of methods have been proposed recently. In this paper, the methods of integrating ground and aerial meta-data for localization and reconstruction are reviewed respectively. Though many intermediate results with high quality have been achieved, we hope that inspired by the reviewed methods in this paper, more thorough methods and impressive results would emerge.

Ancient Chinese architecture 3D preservation by merging ground and aerial point clouds

Ancient Chinese architecture 3D digitalization and documentation is a challenging task for the image based modeling community due to its architectural complexity and structural delicacy. Currently, an effective approach to ancient Chinese architecture 3D reconstruction is to merge the two point clouds, separately obtained from ground and aerial images by the SfM technique. There are two understanding issues should be specially addressed: (1) it is difficult to find the point matches between the images from different sources due to their remarkable variations in viewpoint and scale; (2) due to the inevitable drift phenomenon in any SfM reconstruction process, the resulting two point clouds are no longer strictly related by a single similarity transformation as it should be theoretically. To address these two issues, a new point cloud merging method is proposed in this work. Our method has the following characteristics: (1) the images are matched by leveraging sparse mesh based image synthesis; (2) the putative point matches are filtered by geometrical consistency check and geometrical model verification; and (3) the two point clouds are merged via bundle adjustment by linking the ground-to-aerial tracks. Extensive experiments show that our method outperforms many of the state-of-the-art approaches in terms of ground-to-aerial image matching and point cloud merging.