Systematic Comparison of Power Line Classification Methods from ALS and MLS Point Cloud Data

Sampling-based search algorithms such as Rapidly-Exploring Random Trees (RRT) have been utilized for mobile robot path planning and motion planning in high dimensional continuous spaces. This paper presents a path planning method for a planetary exploration rover in rough terrain. The proposed method exploits the framework of a sampling-based search, the optimal RRT (RRT*) algorithm. The terrain geometry used for planning is composed of point cloud data close to continuous space captured by a light detection and ranging (LIDAR) sensor. During the path planning phase, the proposed RRT*algorithm directly samples a point (node) from the LIDAR point cloud data. The path planner then considers the rough terrain traversability of the rover during the tree expansion process of RRT*. This process improves conventional RRT*in that the generated path is safe and feasible for the rover in rough terrain. In this paper, simulation study on the proposed path planning algorithm in various real terrain data confirms its usefulness.

Large trees are important to a wide variety of wildlife, including many species of conservation concern, such as the California spotted owl (Strix occidentalis occidentalis). Light detection and ranging (LiDAR) has been successfully utilized to identify the density of large‐diameter trees, either by segmenting the LiDARpoint cloud into individual trees, or by building regression models between variables extracted from the LiDARpoint cloud and field data. Neither of these methods is easily accessible for most land managers due to the reliance on specialized software, and much available LiDARdata are being underutilized due to the steep learning curve required for advanced processing using these programs. This study derived a simple, yet effective method for estimating the density of large‐stemmed trees from the LiDARcanopy height model, a standard raster product derived from the LiDARpoint cloud that is often delivered with the LiDARand is easy to process by personnel trained in geographic information systems (GIS). Ground plots needed to be large (1 ha) to build a robust model, but the spatial accuracy of plot center was less crucial to model accuracy. We also showed that predicted large tree density is positively linked to California spotted owl nest sites.

Differential LiDAR (Light Detection and Ranging) from repeated surveys has recently emerged as an effective tool to measure three-dimensional (3D) change for applications, such as quantifying slip and spatially distributed warping associated with earthquake ruptures, and examining the spatial distribution of beach erosion after hurricane impact. Currently, the primary method for determining 3D change from LiDAR is through the use of the iterative closest point (ICP) algorithm and its variants. However, all current studies using ICP have assumed that all LiDAR points in the compared point clouds have uniform accuracy. This assumption is simplistic given that the error for each LiDAR point is variable, and dependent upon time varying factors such as target range, angle of incidence, and aircraft trajectory accuracy. Therefore, to rigorously determine spatial change, it would be ideal to model the random error for every LiDAR observation in the differential point cloud, and use these error estimates as apriori weights in the ICP algorithm. To test this approach, we implemented a rigorous LiDAR observation error propagation method to generate estimated random error for each point in a LiDAR point cloud, and then determine 3D displacements between two point clouds using an anisotropic weighted ICP (A-ICP) algorithm. The algorithm was evaluated by qualitatively and quantitatively comparing point clouds with synthetic fault ruptures between a uniform weight and anistropically weighted ICP algorithm. Then post-earthquake slip is estimated for the 2010 El Mayor-Cucapah Earthquake (EMC), using pre- and post-event LiDAR. Based on the analysis, Moving Window A-ICP is able to better estimate the synthetic surface ruptures, and provides a smoother estimate of actual displacement for the EMC earthquake.

This paper investigates the possibility of applying light detection and ranging (LiDAR) point clouds and geographic information system (GIS) analyses for land use and land cover (LULC) change detection, mainly with a view to monitoring uncontrolled forest succession occurring on postagricultural lands. The research was conducted in a part of the administrative district of Milicz (in the central-west area of Poland). The areas of interest were parcels in which agricultural use has been abandoned and forest succession processes have progressed. The airborne laser scanning (ALS) data (acquired in 2007, 2012, and 2015) revealed detailed changes in land cover as a result of the progression in the forest succession process. Using the ALS data, the LULC changes and the progress of secondary forest succession are shown, and the vegetation parameters (LiDAR metrics) are presented.

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.

Rice canopy height and density are directly usable crop phenotypic traits for the direct estimation of crop biomass. Therefore, it is crucial to rapidly and accurately estimate these phenotypic parameters. To achieve the non-destructive detection and estimation of these essential parameters in rice, a platform based on LiDAR (Light Detection and Ranging) point cloud data for rice phenotypic parameter detection was established. Data collection of rice canopy layers was performed across multiple plots. The LiDAR-detected canopy-top point clouds were selected using a method based on the highest percentile, and a surface model of the canopy was calculated. The canopy height estimation was the difference between the ground elevation and the percentile value. To determine the optimal percentile that would define the rice canopy top, testing was conducted incrementally at percentile values from 0.8 to 1, with increments of 0.005. The optimal percentile value was found to be 0.975. The root mean square error (RMSE) between the LiDAR-detected and manually measured canopy heights for each case was calculated. The prediction model based on canopy height (R2 = 0.941, RMSE = 0.019) exhibited a strong correlation with the actual canopy height. Linear regression analysis was conducted between the gap fractions of different plots, and the average rice canopy Leaf Area Index (LAI) was manually detected. Prediction models of canopy LAIs based on ground return counts (R2 = 0.24, RMSE = 0.1) and ground return intensity (R2 = 0.28, RMSE = 0.09) showed strong correlations but had lower correlations with rice canopy LAIs. Regression analysis was performed between LiDAR-detected canopy heights and manually measured rice canopy LAIs. The results thereof indicated that the prediction model based on canopy height (R2 = 0.77, RMSE = 0.03) was more accurate.

Single tree detection is important for monitoring tree plantations in order to estimate crop yield, which can be used for assessing food and biofuels. In the field of remote sensing, there have been studies regarding single tree extraction using Light Detection and Ranging (LiDAR) point cloud data. Canopy Height Model (CHM) can be simply derived from these LiDAR data where trees can be analysed using different physical characteristics such as tree crown width, and height. However, using these physical characteristics can’t be very useful for identifying which trees are within a plantation, a forest, or a single tree. This is the motivation for developing algorithms of automated differentiation of random trees from plantation trees. Object Based Image Analysis (OBIA) was used to acquire the locations of individual trees. Trees were separated from other land cover in the image using a CHM derived from LiDAR point cloud data. Using watershed algorithm in eCognition, trees with good canopy spacing was easily distinguished. A spatial point pattern analysis was done from the extracted locations of trees to differentiate regularly patterned points from randomly distributed points. Nearest neighbour statistics was done to provide measurement of the distribution of the extracted points. The Z-Score parameter from nearest neighbor was then added to the layers in eCognition as supplement to the available height derivatives such as mean, standard deviation, and different textural parameters. Supervised type of classification was used in order to classify the trees on the image. Training samples of each tree from the image were entered in Support Vector Machine (SVM) to classify the different trees. Two sets of validation were done to compare the results of using the object parameters only, and the object parameters and Z-Score. Addition of the Z-Score from the object parameters increased the obtained accuracy on both validation sets. Classification accuracy based on validation set 1 and set 2 increased by about 20% and 6%, respectively. Additional spatial pattern analysis methods and validation can further prove the use of such layers in improving classification of trees.

NRLI-UAV: Non-rigid registration of sequential raw laser scans and images for low-cost UAV LiDAR point cloud quality improvement

This paper presents a new algorithm for building an indoor map by integrating point clouds of 2D light detection and ranging (LIDAR) scanners in indoor environments. Iterative closest point (ICP) algorithm is one of the well-known methods for such purpose and often used for mobile robot SLAM. However, the algorithm is designed based on dense (or continuous) measurement of the same space with known relative positions of measurement points and angles, and it does not often work efficiently if the measurement is sparse and/or LIDAR locations are unknown. Such situations are seen when some installed LIDARs in a room are used to build a background indoor map for object tracking, or mobile LIDARs are used by technicians to build a digital indoor map, where each space is captured only at a few locations with different angles. To tackle this issue, our method extracts line segments and edge points as features from given LIDAR point clouds and finds shape coincidences commonly contained in a pair of given point clouds to identify positional relationships between LIDARs. By this information, these point clouds can be integrated into common 2D coordinates. Indoor map generation is realized by sequentially applying this integration procedure to every pair of point clouds. Also, the experiments on real data show that our method can identify the relative positions of LIDARs with 10cm-order errors in average, and by sequentially applying the point-cloud integration, the generated maps have only 3% errors.

Abstract. Trees in green areas offer numerous benefits for the environment and human health. Up-to-date, information about trees in urban green areas is crucial for sustainable urban planning. Traditionally, the detection and inventory of urban trees have been conducted through field surveys and terrestrial measurements. However, this labour-intensive approach can be replaced with the more efficient LiDAR (Light Detection and Ranging) systems, an active remote sensing technology. Urban trees can be quickly and automatically determined using 3-dimensional (3D) LiDAR point cloud data. The objective of this study is to acquire trees in densely populated areas of large cities using raw LiDAR data. The urban study area was chosen in the Fatih district of Istanbul, which includes Sultanahmet Square, a site registered on the UNESCO World Heritage List. To detect urban trees, initially, eight classes representing the ground surface were obtained from LiDAR data with a point-based classification approach which is called hierarchical rule-based classification, and the high vegetation class was separated from the other classes. Noise points, which did not correspond to urban trees within the high vegetation class, were removed using the machine learning-based Density-Based Spatial Clustering of Applications with Noise (DBSCAN) clustering algorithm. The remaining high vegetation points were subsequently segmented using the machine learning-based Mean Shift clustering algorithm to obtain individual tree crowns. An accuracy assessment was conducted through completeness and correctness analyses, demonstrating the effectiveness of the proposed point-based approach for the automatic detection of urban trees from LiDAR data. According to the proposed Mean Shift clustering approach, the completeness was 60% and the correctness was 77.42% in test area A, while in test area B, the completeness was 62.30% and the correctness was 80.85%. The much higher completeness (78.26%) and correctness (100%) values were obtained for street trees with regular structure in test area B in comparison with the proposed Mean Shift clustering approaches.

The Light detection and ranging (LiDAR) sensor is used for perceiving the environment of an autonomous vehicle. LiDAR data or point cloud is processed to get the obstacles and their speed around an autonomous vehicle. Based on the information retrieved from LiDAR data and the data from other sensors, real-time decisions are taken for the proper navigation. Hence, the time taken in LiDAR data processing should be minimized. One of the important steps for LiDAR data processing is the segmentation of the obstacles. In this paper, we present a quantitative comparison between two different approaches for point cloud segmentation, Euclidean distance-based Cluster Extraction and Cylindrical range image-based method. Based on the simulation performed on ROS (Robot Operating System) platform, we found that the second method is much faster as compared to the first method. In addition to that, the second method can perform proper segmentation at a larger distance from the sensor.

The large number of object categories and many overlapping or closely neighboring objects in large-scale urban scenes pose great challenges in point cloud classification. Most works in deep learning have achieved a great success on regular input representations, but they are hard to be directly applied to classify point clouds due to the irregularity and inhomogeneity of the data. In this paper, a deep neural network with spatial pooling (DNNSP) is proposed to classify large-scale point clouds without rasterization. The DNNSP first obtains the point-based feature descriptors of all points in each point cluster. The distance minimum spanning tree-based pooling is then applied in the point feature representation to describe the spatial information among the points in the point clusters. The max pooling is next employed to aggregate the point-based features into the cluster-based features. To assure the DNNSP is invariant to the point permutation and sizes of the point clusters, the point-based feature representation is determined by the multilayer perception (MLP) and the weight sharing for each point is retained, which means that the weight of each point in the same layer is the same. In this way, the DNNSP can learn the features of points scaled from the entire regions to the centers of the point clusters, which makes the point cluster-based feature representations robust and discriminative. Finally, the cluster-based features are input to another MLP for point cloud classification. We have evaluated qualitatively and quantitatively the proposed method using several airborne laser scanning and terrestrial laser scanning point cloud data sets. The experimental results have demonstrated the effectiveness of our method in improving classification accuracy.

Automatic extraction of buildings from airborne laser scanning (ALS) point clouds is essential for 3D building reconstruction. This paper presents a two-part approach for extracting buildings from ALS data. First, building objects are extracted from ALS data by a marked point process using the Gibbs energy model of buildings and sampled by a reversible jump Markov chain Monte Carlo algorithm. Second, a refinement operation is performed to filter the non-building points and false building objects before extracting buildings from the detected building objects. Experimental results and evaluation using ISPRS benchmark data-sets showed the robustness of the proposed method.

Routine bridge inspections require labor intensive and highly subjective visual interpretation to determine bridge deck surface condition. Light Detection and Ranging (LiDAR) a relatively new class of survey instrument has become a popular and increasingly used technology for providing as-built and inventory data in civil applications. While an increasing number of private and governmental agencies possess terrestrial and mobile LiDAR systems, an understanding of the technology’s capabilities and potential applications continues to evolve. LiDAR is a line-of-sight instrument and as such, care must be taken when establishing scan locations and resolution to allow the capture of data at an adequate resolution for defining features that contribute to the analysis of bridge deck surface condition. Information such as the location, area, and volume of spalling on deck surfaces, undersides, and support columns can be derived from properly collected LiDAR point clouds. The LiDAR point clouds contain information that can provide quantitative surface condition information, resulting in more accurate structural health monitoring. LiDAR scans were collected at three study bridges, each of which displayed a varying degree of degradation. A variety of commercially available analysis tools and an independently developed algorithm written in ArcGIS Python (ArcPy) were used to locate and quantify surface defects such as location, volume, and area of spalls. The results were visual and numerically displayed in a user-friendly web-based decision support tool integrating prior bridge condition metrics for comparison. LiDAR data processing procedures along with strengths and limitations of point clouds for defining features useful for assessing bridge deck condition are discussed. Point cloud density and incidence angle are two attributes that must be managed carefully to ensure data collected are of high quality and useful for bridge condition evaluation. When collected properly to ensure effective evaluation of bridge surface condition, LiDAR data can be analyzed to provide a useful data set from which to derive bridge deck condition information.

Filtering of airborne laser scanning (ALS) point clouds into ground and nonground points is a core postprocessing step for ALS data. A hierarchical filtering method, which has high operating efficiency and accuracy because of the combination of multiscale morphology and progressive triangulated irregular network (TIN) densification (PTD), is proposed. In the proposed method, the grid is first constructed for the ALS point clouds, and virtual seed points are set by analyzing the shape and elevation distribution of points within the grid. Then, the virtual seed points are classified as ground or nonground using the multiscale morphological method. Finally, the virtual ground seed points are utilized to generate the initial TIN, and the filter is completed by iteratively densifying the initial TIN. We used various ALS data to test the performance of the proposed method. The experimental results show that the proposed filtering method has strong applicability for a variety of landscapes and, in particular, has lower commission error than the classical PTD filtering method in urban areas.