scholarly journals A Novel Vegetation Point Cloud Density Tree-Segmentation Model for Overlapping Crowns Using UAV LiDAR

2021 ◽  
Vol 13 (8) ◽  
pp. 1442
Author(s):  
Kaisen Ma ◽  
Yujiu Xiong ◽  
Fugen Jiang ◽  
Song Chen ◽  
Hua Sun
Keyword(s):  
Point Cloud ◽  
Local Maximum ◽  
Window Size ◽  
Point Clouds ◽  
High Density ◽  
Watershed Algorithm ◽  
Canopy Area ◽  
Individual Trees ◽  
Optimal Window ◽  
Cloud Density

Detecting and segmenting individual trees in forest ecosystems with high-density and overlapping crowns often results in bias due to the limitations of the commonly used canopy height model (CHM). To address such limitations, this paper proposes a new method to segment individual trees and extract tree structural parameters. The method involves the following key steps: (1) unmanned aerial vehicle (UAV)-scanned, high-density laser point clouds were classified, and a vegetation point cloud density model (VPCDM) was established by analyzing the spatial density distribution of the classified vegetation point cloud in the plane projection; and (2) a local maximum algorithm with an optimal window size was used to detect tree seed points and to extract tree heights, and an improved watershed algorithm was used to extract the tree crowns. The proposed method was tested at three sites with different canopy coverage rates in a pine-dominated forest in northern China. The results showed that (1) the kappa coefficient between the proposed VPCDM and the commonly used CHM was 0.79, indicating that performance of the VPCDM is comparable to that of the CHM; (2) the local maximum algorithm with the optimal window size could be used to segment individual trees and obtain optimal single-tree segmentation accuracy and detection rate results; and (3) compared with the original watershed algorithm, the improved watershed algorithm significantly increased the accuracy of canopy area extraction. In conclusion, the proposed VPCDM may provide an innovative data segmentation model for light detection and ranging (LiDAR)-based high-density point clouds and enhance the accuracy of parameter extraction.

scholarly journals Advances in the Derivation of Northeast Siberian Forest Metrics Using High-Resolution UAV-Based Photogrammetric Point Clouds

2019 ◽  
Vol 11 (12) ◽  
pp. 1447 ◽  
Author(s):  
Frederic Brieger ◽  
Ulrike Herzschuh ◽  
Luidmila A. Pestryakova ◽  
Bodo Bookhagen ◽  
Evgenii S. Zakharov ◽  
...  
Keyword(s):  
High Resolution ◽  
Forest Structure ◽  
Stand Structure ◽  
Structural Information ◽  
Carbon Sink ◽  
Local Maximum ◽  
Window Size ◽  
Point Clouds ◽  
Percentage Error ◽  
Individual Tree

Forest structure is a crucial component in the assessment of whether a forest is likely to act as a carbon sink under changing climate. Detailed 3D structural information about the tundra–taiga ecotone of Siberia is mostly missing and still underrepresented in current research due to the remoteness and restricted accessibility. Field based, high-resolution remote sensing can provide important knowledge for the understanding of vegetation properties and dynamics. In this study, we test the applicability of consumer-grade Unmanned Aerial Vehicles (UAVs) for rapid calculation of stand metrics in treeline forests. We reconstructed high-resolution photogrammetric point clouds and derived canopy height models for 10 study sites from NE Chukotka and SW Yakutia. Subsequently, we detected individual tree tops using a variable-window size local maximum filter and applied a marker-controlled watershed segmentation for the delineation of tree crowns. With this, we successfully detected 67.1% of the validation individuals. Simple linear regressions of observed and detected metrics show a better correlation (R2) and lower relative root mean square percentage error (RMSE%) for tree heights (mean R2 = 0.77, mean RMSE% = 18.46%) than for crown diameters (mean R2 = 0.46, mean RMSE% = 24.9%). The comparison between detected and observed tree height distributions revealed that our tree detection method was unable to representatively identify trees <2 m. Our results show that plot sizes for vegetation surveys in the tundra–taiga ecotone should be adapted to the forest structure and have a radius of >15–20 m to capture homogeneous and representative forest stands. Additionally, we identify sources of omission and commission errors and give recommendations for their mitigation. In summary, the efficiency of the used method depends on the complexity of the forest’s stand structure.

scholarly journals Detection of Very Small Tree Plantations and Tree-Level Characterization Using Open-Access Remote-Sensing Databases

2020 ◽  
Vol 12 (14) ◽  
pp. 2276
Author(s):  
Laura Alonso ◽  
Juan Picos ◽  
Guillermo Bastos ◽  
Julia Armesto
Keyword(s):  
Open Access ◽  
Point Cloud ◽  
Castanea Sativa ◽  
Point Clouds ◽  
Coefficient Of Determination ◽  
National Database ◽  
Tree Level ◽  
Tree Plantations ◽  
Support Vector ◽  
Individual Trees

Highly fragmented land property hinders the planning and management of single species tree plantations. In such situations, acquiring information about the available resources is challenging. This study aims to propose a method to locate and characterize tree plantations in these cases. Galicia (Northwest of Spain) is an area where property is extremely divided into small parcels. European chestnut (Castanea sativa) plantations are an important source of income there; however, it is often difficult to obtain information about them due to their small size and scattered distribution. Therefore, we selected a Galician region with a high presence of chestnut plantations as a case study area in order to locate and characterize small plantations using open-access data. First, we detected the location of chestnut plantations applying a supervised classification for a combination of: Sentinel-2 images and the open-access low-density Light Detection and Ranging (LiDAR) point clouds, obtained from the untapped open-access LiDAR Spanish national database. Three classification algorithms were used: Random Forest (RF), Support Vector Machine (SVM), and XGBoost. We later characterized the plots at the tree-level using the LiDAR point-cloud. We detected individual trees and obtained their height applying a local maxima algorithm to a point-cloud-derived Canopy Height Model (CHM). We also calculated the crown surface of each tree by applying a method based on two-dimensional (2D) tree shape reconstruction and canopy segmentation to a projection of the LiDAR point cloud. Chestnut plantations were detected with an overall accuracy of 81.5%. Individual trees were identified with a detection rate of 96%. The coefficient of determination R2 value for tree height estimation was 0.83, while for the crown surface calculation it was 0.74. The accuracy achieved with these open-access databases makes the proposed procedure suitable for acquiring knowledge about the location and state of chestnut plantations as well as for monitoring their evolution.

scholarly journals CANOPY LIDAR POINT CLOUD DATA K-MEANS CLUSTERING WATERSHED SEGMENTATION METHOD

2020 ◽  
Vol VI-3/W1-2020 ◽  
pp. 67-73
Author(s):  
Y. Mu ◽  
G. Zhou ◽  
H. Wang
Keyword(s):  
Point Cloud ◽  
Clustering Algorithm ◽  
Local Maximum ◽  
Tree Canopy ◽  
Second Step ◽  
Watershed Algorithm ◽  
Target Area ◽  
Cloud Data ◽  
Single Tree ◽  
Variable Window

Abstract. Airborne laser LiDAR has widely applied in the accurate extraction of single tree canopy for inventory of precision forestry. Due to the over-segmentation phenomenon occurring in the traditional watershed single-wood segmentation, this paper presents a method, called K – means clustering watershed for single tree segmentation. This method consists of four aspects: The first step is to filter the point cloud to eliminate the interference factors such as ground elevation and other factors that interfere with the LiDAR point cloud segmentation; The second step is to optimize the generation of CHM, generate a CMM based on CHM variable window detection, and obtain the treetop position to provide the pixel center position for subsequent K – means cluster segmentation; The third step is to use the K – means clustering algorithm to perform initial cluster segmentation to extract the target pixels of interest. At this time, the local maximum value detected by the variable window in the second step is used as the center pixel of the cluster; In the fourth step, an improved watershed algorithm based on the similarity of 4 neighborhoods is proposed. The improved watershed algorithm is applied to the K – means initial clustering image to segment the target area, and the over-segmentation results are subsequently processed, and the over-segmentation blocks are combined according to certain criteria. Identify the contour of single canopy from the CHM images of the experimental forest data. The experimental results show that the proposed algorithm can effectively solve the over-segmentation problem happening the traditional watershed algorithm. The accuracy of F, R and P parameters can be improved by 7.1%, 11% and 9.8%.

scholarly journals Effects of LiDAR Point Density on Extraction of Traffic Signs: A Sensitivity Study

2019 ◽  
Vol 2673 (1) ◽  
pp. 41-51 ◽  
Author(s):  
Suliman Gargoum ◽  
Karim El-Basyouny
Keyword(s):  
Point Cloud ◽  
Point Clouds ◽  
Sensitivity Study ◽  
Angle Of Incidence ◽  
Traffic Signs ◽  
Detection Rates ◽  
Point Density ◽  
Dense Point ◽  
Different Levels ◽  
Cloud Density

Datasets collected using light detection and ranging (LiDAR) technology often consist of dense point clouds. However, the density of the point cloud could vary depending on several different factors including the capabilities of the data collection equipment, the conditions in which data are collected, and other features such as range and angle of incidence. Although variation in point density is expected to influence the quality of the information extracted from LiDAR, the extent to which changes in density could affect the extraction is unknown. Understanding such impacts is essential for agencies looking to adopt LiDAR technology and researchers looking to develop algorithms to extract information from LiDAR. This paper focuses specifically on understanding the impacts of point density on extracting traffic signs from LiDAR datasets. The densities of point clouds are first reduced using stratified random sampling; traffic signs are then extracted from those datasets at different levels of point density. The precision and accuracy of the detection process was assessed at the different levels of point cloud density and on four different highway segments. In general, it was found that for signs with large panels along the approach on which LiDAR data were collected, reducing the point cloud density by up to 70% of the original point cloud had minimal impacts on the sign detection rates. Results of this study provide practical guidance to transportation agencies interested in understanding the tradeoff in price, quality, and coverage, when acquiring LiDAR equipment for the inventory of traffic signs on their transportation networks.

scholarly journals Quantitative Comparison of UAS-Borne LiDAR Systems for High-Resolution Forested Wetland Mapping

Sensors ◽  
2020 ◽  
Vol 20 (16) ◽  
pp. 4453
Author(s):  
Narcisa Gabriela Pricope ◽  
Joanne Nancie Halls ◽  
Kerry Lynn Mapes ◽  
Joseph Britton Baxley ◽  
James JyunYueh Wu
Keyword(s):  
High Resolution ◽  
Point Cloud ◽  
Coastal Wetland ◽  
Coniferous Forest ◽  
Point Clouds ◽  
Atlantic Coastal Plain ◽  
Airborne Lidar ◽  
Forested Wetland ◽  
Variable Cost ◽  
Cloud Density

Wetlands provide critical ecosystem services across a range of environmental gradients and are at heightened risk of degradation from anthropogenic pressures and continued development, especially in coastal regions. There is a growing need for high-resolution (spatially and temporally) habitat identification and precise delineation of wetlands across a variety of stakeholder groups, including wetlands loss mitigation programs. Traditional wetland delineations are costly, time-intensive and can physically degrade the systems that are being surveyed, while aerial surveys are relatively fast and relatively unobtrusive. To assess the efficacy and feasibility of using two variable-cost LiDAR sensors mounted on a commercial hexacopter unmanned aerial system (UAS) in deriving high resolution topography, we conducted nearly concomitant flights over a site located in the Atlantic Coastal plain that contains a mix of palustrine forested wetlands, upland coniferous forest, upland grass and bare ground/dirt roads. We compared point clouds and derived topographic metrics acquired using the Quanergy M8 and the Velodyne HDL-32E LiDAR sensors with airborne LiDAR and results showed that the less expensive and lighter payload sensor outperforms the more expensive one in deriving high resolution, high accuracy ground elevation measurements under a range of canopy cover densities and for metrics of point cloud density and digital terrain computed both globally and locally using variable size tessellations. The mean point cloud density was not significantly different between wetland and non-wetland areas, but the two sensors were significantly different by wetland/non-wetland type. Ultra-high-resolution LiDAR-derived topography models can fill evolving wetlands mapping needs and increase accuracy and efficiency of detection and prediction of sensitive wetland ecosystems, especially for heavily forested coastal wetland systems.

scholarly journals EXPLORING CROSS-CITY SEMANTIC SEGMENTATION OF ALS POINT CLOUDS

2021 ◽  
Vol XLIII-B2-2021 ◽  
pp. 247-254
Author(s):  
Y. Xie ◽  
K. Schindler ◽  
J. Tian ◽  
X. X. Zhu
Keyword(s):  
Point Cloud ◽  
Laser Scanning ◽  
Data Augmentation ◽  
Poor Performance ◽  
Semantic Segmentation ◽  
Point Clouds ◽  
Training Data ◽  
The Impact ◽  
Cloud Density ◽  
Deep Coral

Abstract. Deep learning models achieve excellent semantic segmentation results for airborne laser scanning (ALS) point clouds, if sufficient training data are provided. Increasing amounts of annotated data are becoming publicly available thanks to contributors from all over the world. However, models trained on a specific dataset typically exhibit poor performance on other datasets. I.e., there are significant domain shifts, as data captured in different environments or by distinct sensors have different distributions. In this work, we study this domain shift and potential strategies to mitigate it, using two popular ALS datasets: the ISPRS Vaihingen benchmark from Germany and the LASDU benchmark from China. We compare different training strategies for cross-city ALS point cloud semantic segmentation. In our experiments, we analyse three factors that may lead to domain shift and affect the learning: point cloud density, LiDAR intensity, and the role of data augmentation. Moreover, we evaluate a well-known standard method of domain adaptation, deep CORAL (Sun and Saenko, 2016). In our experiments, adapting the point cloud density and appropriate data augmentation both help to reduce the domain gap and improve segmentation accuracy. On the contrary, intensity features can bring an improvement within a dataset, but deteriorate the generalisation across datasets. Deep CORAL does not further improve the accuracy over the simple adaptation of density and data augmentation, although it can mitigate the impact of improperly chosen point density, intensity features, and further dataset biases like lack of diversity.

scholarly journals 3D Change Detection Using Adaptive Thresholds Based on Local Point Cloud Density

2021 ◽  
Vol 10 (3) ◽  
pp. 127
Author(s):  
Dan Liu ◽  
Dajun Li ◽  
Meizhen Wang ◽  
Zhiming Wang
Keyword(s):  
Change Detection ◽  
Point Cloud ◽  
Model Updating ◽  
Average Distance ◽  
Point Clouds ◽  
Density Variation ◽  
Local Point ◽  
Disaster Assessment ◽  
Adaptive Thresholds ◽  
Cloud Density

In recent years, because of highly developed LiDAR (Light Detection and Ranging) technologies, there has been increasing demand for 3D change detection in urban monitoring, urban model updating, and disaster assessment. In order to improve the effectiveness of 3D change detection based on point clouds, an approach for 3D change detection using point-based comparison is presented in this paper. To avoid density variation in point clouds, adaptive thresholds are calculated through the k-neighboring average distance and the local point cloud density. A series of experiments for quantitative evaluation is performed. In the experiments, the influencing factors including threshold, registration error, and neighboring number of 3D change detection are discussed and analyzed. The results of the experiments demonstrate that the approach using adaptive thresholds based on local point cloud density are effective and suitable.

Geometric Quality Indicators for Scanned Point Clouds

2012 ◽  
Vol 523-524 ◽  
pp. 901-906
Author(s):  
Hiromasa Suzuki ◽  
Yutaka Ohtake ◽  
Shusaku Shibata ◽  
Takashi Michikawa
Keyword(s):  
Quality Indicators ◽  
Point Cloud ◽  
Point Clouds ◽  
Different Types ◽  
Geometric Quality ◽  
Cloud Thickness ◽  
Cloud Density

We propose geometric quality indicators for evaluating the quality of point clouds (sets of scanned points). These indicators represent aspects of quality often considered in practical scanning procedures, such as cloud thickness and cloud density. We defined the indicators mathematically and developed software to compute them, then conducted experiments to evaluate the indicators for point clouds obtained by scanning the same samples with different types of surface scanners and scanning procedures. The results showed that the indicators are capable of highlighting various aspects of point cloud quality.

A Fast Reconstruction of Dense Unorganized Point Cloud Based on 3-Color Octree

2009 ◽  
Vol 628-629 ◽  
pp. 293-298 ◽  
Author(s):  
H.M. Zhou ◽  
Z.G. Liu ◽  
M.X. Li ◽  
B.H. Lu
Keyword(s):  
Point Cloud ◽  
Reconstruction Algorithm ◽  
Point Clouds ◽  
Watershed Algorithm ◽  
Triangular Meshes ◽  
Boundary Node ◽  
Model Based ◽  
Implicit Model ◽  
Interior Boundary ◽  
Fast Reconstruction

This paper describes a fast reconstruction algorithm of implicit model based on 3-color octree structure for dense unorganized point cloud. At first, the point cloud is stored with an extended octree, 3-color octree. Aiming at this 3-color octree structure a new node watershed algorithm is presented with a higher efficiency to estimate the signs of subdivided leaf nodes. So the leaf nodes are divided into three types: interior, boundary and exterior nodes. To quickly reconstruct the model we sample the 3-color octree structure only at boundary nodes, which greatly reduces the number of sampled points. Then, the triangular meshes are extracted according to the relationships of boundary node. Finally the applications are illustrated in several point clouds, which shows the efficiency and precision of this reconstruction algorithm.

scholarly journals THE IMPACT OF POINT CLOUD DENSITY ON BUILDING OUTLINE EXTRACTION

2020 ◽  
Vol XLIII-B2-2020 ◽  
pp. 407-413 ◽  
Author(s):  
U. Drešček ◽  
M. Kosmatin Fras ◽  
A. Lisec ◽  
D. Grigillo
Keyword(s):  
Point Cloud ◽  
Point Clouds ◽  
Direct Approach ◽  
Factors Affecting ◽  
Dense Image ◽  
Data Driven Approach ◽  
Aerial Vehicle ◽  
Outline Extraction ◽  
The Impact ◽  
Cloud Density

Abstract. Recently, building outline extraction from point cloud has gained momentum in particular in the context of 3D building modelling based on a data-driven approach, which has also been our motivation. For an accurate building outline extraction from a point cloud, various factors affecting the quality should be considered. In this research, we analysed the influence of point cloud density on the quality of the extracted building outlines. The input data was a classified photogrammetric point cloud, obtained from the dense image matching of images acquired by an optical sensor mounted on the unmanned aerial vehicle (UAV). For outline extraction, we selected two procedures, namely the direct approach and the raster approach. In the direct approach, building outlines are extracted directly from the points that have been classified as buildings. First, a convex hull with the alpha algorithm is estimated, which is further generalised with the Douglas-Peucker algorithm. This is followed by the shape regularisation to ensure perpendicular angles of the outline. In the raster approach, we first rasterised the building points and then extracted the building outlines using the Hough transform. In both approaches, the result is a roof outline in a 2D plane representing the maximum extent of the building above the surface. The building outlines were extracted from point clouds with five different densities. For both approaches, the quality assessment has shown that point cloud density has an impact on the building outline extraction, especially on the completeness of the outlines.

Sign in / Sign up

Export Citation Format

Share Document