scholarly journals Wood–leaf Classification of Tree Point Cloud Based on Intensity and Geometric Information

2021 ◽  
Vol 13 (20) ◽  
pp. 4050
Author(s):  
Jingqian Sun ◽  
Pei Wang ◽  
Zhiyong Gao ◽  
Zichu Liu ◽  
Yaxin Li ◽  
...  
Keyword(s):  
Point Cloud ◽  
High Speed ◽  
Laser Scanning ◽  
Structural Parameters ◽  
Point Clouds ◽  
Neighborhood Density ◽  
Geometric Information ◽  
Classification Technique ◽  
Manual Classification

Terrestrial laser scanning (TLS) can obtain tree point clouds with high precision and high density. The efficient classification of wood points and leaf points is essential for the study of tree structural parameters and ecological characteristics. Using both intensity and geometric information, we present an automated wood–leaf classification with a three-step classification and wood point verification. The tree point cloud was classified into wood points and leaf points using intensity threshold, neighborhood density and voxelization successively, and was then verified. Twenty-four willow trees were scanned using the RIEGL VZ-400 scanner. Our results were compared with the manual classification results. To evaluate the classification accuracy, three indicators were introduced into the experiment: overall accuracy (OA), Kappa coefficient (Kappa), and Matthews correlation coefficient (MCC). The ranges of OA, Kappa, and MCC of our results were from 0.9167 to 0.9872, 0.7276 to 0.9191, and 0.7544 to 0.9211, respectively. The average values of OA, Kappa, and MCC were 0.9550, 0.8547, and 0.8627, respectively. The time costs of our method and another were also recorded to evaluate the efficiency. The average processing time was 1.4 seconds per million points for our method. The results show that our method represents a potential wood–leaf classification technique with the characteristics of automation, high speed, and good accuracy.

scholarly journals ON A KNOWLEDGE-BASED APPROACH TO THE CLASSIFICATION OF MOBILE LASER SCANNING POINT CLOUDS

2018 ◽  
Vol XLII-4 ◽  
pp. 343-349 ◽  
Author(s):  
M. Lemmens
Keyword(s):  
Point Cloud ◽  
Laser Scanning ◽  
Decision Rules ◽  
Point Clouds ◽  
Bench Mark ◽  
Automated Classification ◽  
Initial Experiment ◽  
Data Set ◽  
Knowledge Based

<p><strong>Abstract.</strong> A knowledge-based system exploits the knowledge, which a human expert uses for completing a complex task, through a database containing decision rules, and an inference engine. Already in the early nineties knowledge-based systems have been proposed for automated image classification. Lack of success faded out initial interest and enthusiasm, the same fate neural networks struck at that time. Today the latter enjoy a steady revival. This paper aims at demonstrating that a knowledge-based approach to automated classification of mobile laser scanning point clouds has promising prospects. An initial experiment exploiting only two features, height and reflectance value, resulted in an overall accuracy of 79<span class="thinspace"></span>% for the Paris-rue-Madame point cloud bench mark data set.</p>

scholarly journals Automating Parameter Learning for Classifying Terrestrial LiDAR Point Cloud Using 2D Land Cover Maps

2018 ◽  
Vol 10 (8) ◽  
pp. 1192 ◽  
Author(s):  
Chen-Chieh Feng ◽  
Zhou Guo
Keyword(s):  
Land Cover ◽  
Point Cloud ◽  
Laser Scanning ◽  
Point Clouds ◽  
Parameter Learning ◽  
Cloud Classification ◽  
Land Cover Map ◽  
Point Cloud Classification ◽  
Optimal Feature

The automating classification of point clouds capturing urban scenes is critical for supporting applications that demand three-dimensional (3D) models. Achieving this goal, however, is met with challenges because of the varying densities of the point clouds and the complexity of the 3D data. In order to increase the level of automation in the point cloud classification, this study proposes a segment-based parameter learning method that incorporates a two-dimensional (2D) land cover map, in which a strategy of fusing the 2D land cover map and the 3D points is first adopted to create labelled samples, and a formalized procedure is then implemented to automatically learn the following parameters of point cloud classification: the optimal scale of the neighborhood for segmentation, optimal feature set, and the training classifier. It comprises four main steps, namely: (1) point cloud segmentation; (2) sample selection; (3) optimal feature set selection; and (4) point cloud classification. Three datasets containing the point cloud data were used in this study to validate the efficiency of the proposed method. The first two datasets cover two areas of the National University of Singapore (NUS) campus while the third dataset is a widely used benchmark point cloud dataset of Oakland, Pennsylvania. The classification parameters were learned from the first dataset consisting of a terrestrial laser-scanning data and a 2D land cover map, and were subsequently used to classify both of the NUS datasets. The evaluation of the classification results showed overall accuracies of 94.07% and 91.13%, respectively, indicating that the transition of the knowledge learned from one dataset to another was satisfactory. The classification of the Oakland dataset achieved an overall accuracy of 97.08%, which further verified the transferability of the proposed approach. An experiment of the point-based classification was also conducted on the first dataset and the result was compared to that of the segment-based classification. The evaluation revealed that the overall accuracy of the segment-based classification is indeed higher than that of the point-based classification, demonstrating the advantage of the segment-based approaches.

Towards the automatic 3D characterization of forest plots

2020 ◽  
Author(s):  
Carlos Cabo ◽  
Celestino Ordoñez ◽  
Covadonga Prendes ◽  
Stefan Doerr ◽  
Jose V. Roces-Diaz ◽  
...  
Keyword(s):  
Point Cloud ◽  
Laser Scanning ◽  
3D Structure ◽  
Tree Height ◽  
Point Clouds ◽  
Forest Plot ◽  
Multiscale Approach ◽  
Plot Structure

&lt;p&gt;Ground-based point clouds (from laser scanning or photogrammetry, and from static or mobile devices) give very detailed 3D information of forest plots. Also, if this information is complemented with data gathered from aerial vehicles, some parts of the forest structure that are not visible from the terrain can be represented (e.g. treetops). However, the heterogeneity of the point clouds, the complexity of some forest plots and the limitations of some data gathering/processing techniques lead to some occlusions and misrepresentations of the features in the plot. Therefore, complete automation of very detailed characterizations of all the items/features/structures in a forest plot is, most of the times, not possible yet.&lt;/p&gt;&lt;p&gt;On one hand, single trees (or small groups of them) can be modelled in detail from dense point clouds (e.g. using quantitative structure models), but this processes usually require &amp;#160;complete absence of leaves and &amp;#160;intense and/or active operator labouring. On the other hand, many methods automate the location of the trees in a plot and the estimation of basic parameters, like the diameters and, sometimes, the total tree height.&lt;/p&gt;&lt;p&gt;We are developing a fully automatic method that lies in between some very accurate but labour-intensive single-tree models, and the mere location and diameter calculation of the trees in a plot. Our method is able to automatically detect and locate the trees in a plot and calculate diameters, but it is also able to characterize the 3D tree structure: stem model, inclination and curvature; inclination and location of the main branches (in some cases); and tree crown individualization and diameter estimation. In addition, our method also classifies the points on understory vegetation.&lt;/p&gt;&lt;p&gt;Our method relies on the integration of algorithms that have been developed by our team, and includes the development of new modules. The first step consists in an initial classification of the point cloud using a multiscale approach based on local shapes. As a result, the point cloud is preliminarily classified into three classes: stems, branches and leaves, and ground. After that, a series of geometric operations lead to the final 3D characterization of the plot structure: (i) stem axes and section modelling (from the pre-classified points on the stems), (ii) distance points-closest stem axis and tree individualization, (iii) extraction and characterization of the main branches, and (iv) final classification of the points laying on stems, main branches, rest of the canopy, understory and ground.&lt;/p&gt;&lt;p&gt;We are testing the algorithm in several forest plots with coniferous and broadleaf trees. Initial results show values of completeness and correctness for tree detection and point classification over 90%.&lt;/p&gt;&lt;p&gt;Currently, there are already several cross-cutting projects using our method&amp;#180;s results as inputs: (i) Automatic calculation of taper functions (use: diameters along the stem and tree height), (ii) wood quality based on shape (use: diameters along the stem and insertion of main branches), and (iii) wildfire behaviour models (use: fuel classification and 3D structure to adapt the data to the format of the existing 3D fuel standard models).&lt;/p&gt;

scholarly journals AUTOMATIC CLASSIFICATION OF TREES FROM LASER SCANNING POINT CLOUDS

2015 ◽  
Vol II-3/W5 ◽  
pp. 137-144 ◽  
Author(s):  
B. Sirmacek ◽  
R. Lindenbergh
Keyword(s):  
Point Cloud ◽  
Laser Scanning ◽  
Point Clouds ◽  
Detection Methods ◽  
Local Maxima ◽  
Advantages And Disadvantages ◽  
Close Proximity ◽  
Point Density ◽  
Grid Surface

Development of laser scanning technologies has promoted tree monitoring studies to a new level, as the laser scanning point clouds enable accurate 3D measurements in a fast and environmental friendly manner. In this paper, we introduce a probability matrix computation based algorithm for automatically classifying laser scanning point clouds into ’tree’ and ’non-tree’ classes. Our method uses the 3D coordinates of the laser scanning points as input and generates a new point cloud which holds a label for each point indicating if it belongs to the ’tree’ or ’non-tree’ class. To do so, a grid surface is assigned to the lowest height level of the point cloud. The grids are filled with probability values which are calculated by checking the point density above the grid. Since the tree trunk locations appear with very high values in the probability matrix, selecting the local maxima of the grid surface help to detect the tree trunks. Further points are assigned to tree trunks if they appear in the close proximity of trunks. Since heavy mathematical computations (such as point cloud organization, detailed shape 3D detection methods, graph network generation) are not required, the proposed algorithm works very fast compared to the existing methods. The tree classification results are found reliable even on point clouds of cities containing many different objects. As the most significant weakness, false detection of light poles, traffic signs and other objects close to trees cannot be prevented. Nevertheless, the experimental results on mobile and airborne laser scanning point clouds indicate the possible usage of the algorithm as an important step for tree growth observation, tree counting and similar applications. While the laser scanning point cloud is giving opportunity to classify even very small trees, accuracy of the results is reduced in the low point density areas further away than the scanning location. These advantages and disadvantages of two laser scanning point cloud sources are discussed in detail.

scholarly journals INTERACTIVE CLASSIFICATION OF CONSTRUCTION MATERIALS: FEEDBACK DRIVEN FRAMEWORK FOR ANNOTATION AND ANALYSIS OF 3D POINT CLOUDS

2017 ◽  
Vol XLII-2/W5 ◽  
pp. 343-347
Author(s):  
M. R. Hess ◽  
V. Petrovic ◽  
F. Kuester
Keyword(s):  
Cultural Heritage ◽  
Point Cloud ◽  
Laser Scanning ◽  
Building Materials ◽  
Point Clouds ◽  
Normal Vector ◽  
Surface Geometry ◽  
Historical Structures ◽  
3D Point Clouds

Digital documentation of cultural heritage structures is increasingly more common through the application of different imaging techniques. Many works have focused on the application of laser scanning and photogrammetry techniques for the acquisition of threedimensional (3D) geometry detailing cultural heritage sites and structures. With an abundance of these 3D data assets, there must be a digital environment where these data can be visualized and analyzed. Presented here is a feedback driven visualization framework that seamlessly enables interactive exploration and manipulation of massive point cloud data. The focus of this work is on the classification of different building materials with the goal of building more accurate as-built information models of historical structures. User defined functions have been tested within the interactive point cloud visualization framework to evaluate automated and semi-automated classification of 3D point data. These functions include decisions based on observed color, laser intensity, normal vector or local surface geometry. Multiple case studies are presented here to demonstrate the flexibility and utility of the presented point cloud visualization framework to achieve classification objectives.

scholarly journals JOINT CLASSIFICATION OF ALS AND DIM POINT CLOUDS

2019 ◽  
Vol XLII-2/W13 ◽  
pp. 1113-1120
Author(s):  
F. Politz ◽  
M. Sester
Keyword(s):  
Transfer Learning ◽  
Point Cloud ◽  
Laser Scanning ◽  
Measurement Techniques ◽  
Point Clouds ◽  
Aerial Images ◽  
Individual Measurement ◽  
Cloud Data ◽  
Practical Applications

<p><strong>Abstract.</strong> National mapping agencies (NMAs) have to acquire nation-wide Digital Terrain Models on a regular basis as part of their obligations to provide up-to-date data. Point clouds from Airborne Laser Scanning (ALS) are an important data source for this task; recently, NMAs also started deriving Dense Image Matching (DIM) point clouds from aerial images. As a result, NMAs have both point cloud data sources available, which they can exploit for their purposes. In this study, we investigate the potential of transfer learning from ALS to DIM data, so the time consuming step of data labelling can be reduced. Due to their specific individual measurement techniques, both point clouds have various distinct properties such as RGB or intensity values, which are often exploited for classification of either ALS or DIM point clouds. However, those features also hinder transfer learning between these two point cloud types, since they do not exist in the other point cloud type. As the mere 3D point is available in both point cloud types, we focus on transfer learning from an ALS to a DIM point cloud using exclusively the point coordinates. We are tackling the issue of different point densities by rasterizing the point cloud into a 2D grid and take important height features as input for classification. We train an encoder-decoder convolutional neural network with labelled ALS data as a baseline and then fine-tune this baseline with an increasing amount of labelled DIM data. We also train the same network exclusively on all available DIM data as reference to compare our results. We show that only 10% of labelled DIM data increase the classification results notably, which is especially relevant for practical applications.</p>

scholarly journals POINT CLOUD CLASSIFICATION BY FUSING SUPERVOXEL SEGMENTATION WITH MULTI-SCALE FEATURES

2019 ◽  
Vol XLII-2/W13 ◽  
pp. 919-925
Author(s):  
W. Ao ◽  
L. Wang ◽  
J. Shan
Keyword(s):  
Point Cloud ◽  
Laser Scanning ◽  
Point Clouds ◽  
Geometric Information ◽  
Multi Scale ◽  
Cloud Classification ◽  
Spatial Consistency ◽  
Class Labels ◽  
Point Cloud Classification ◽  
Robust To Noise

<p><strong>Abstract.</strong> Point cloud classification is quite a challenging task due to the existence of noises, occlusion and various object types and sizes. Currently, the commonly used statistics-based features cannot accurately characterize the geometric information of a point cloud. This limitation often leads to feature confusion and classification mistakes (e.g., points of building corners and vegetation always share similar statistical features in a local neighbourhood, such as curvature, sphericity, etc). This study aims at solving this problem by leveraging the advantage of both the supervoxel segmentation and multi-scale features. For each point, its multi-scale features within different radii are extracted. Simultaneously, the point cloud is partitioned into simple supervoxel segments. After that, the class probability of each point is predicted by the proposed SegMSF approach that combines multi-scale features with the supervoxel segmentation results. At the end, the effect of data noises is supressed by using a global optimization that encourages spatial consistency of class labels. The proposed method is tested on both airborne laser scanning (ALS) and mobile laser scanning (MLS) point clouds. The experimental results demonstrate that the proposed method performs well in terms of classifying objects of different scales and is robust to noise.</p>

scholarly journals ROAD TYPE CLASSIFICATION OF MLS POINT CLOUDS USING DEEP LEARNING

2021 ◽  
Vol XLIII-B2-2021 ◽  
pp. 115-122
Author(s):  
Q. Bai ◽  
R. C. Lindenbergh ◽  
J. Vijverberg ◽  
J. A. P. Guelen
Keyword(s):  
Point Cloud ◽  
Laser Scanning ◽  
Feature Vector ◽  
Point Clouds ◽  
Transport Systems ◽  
Geometric Feature ◽  
Local Geometry ◽  
Road Type ◽  
Type Classification

Abstract. Functional classification of the road is important to the construction of sustainable transport systems and proper design of facilities. Mobile laser scanning (MLS) point clouds provide accurate and dense 3D measurements of road scenes, while their massive data volume and lack of structure also bring difficulties in processing. 3D point cloud understanding through deep neural networks achieves breakthroughs since PointNet and arouses wide attention in recent years. In this paper, we study the automatic road type classification of MLS point clouds by employing a point-wise neural network, RandLA-Net, which is designed for consuming large-scale point clouds. An effective local feature aggregation (LFA) module in RandLA-Net preserves the local geometry in point clouds by formulating an enhanced geometric feature vector and learning different point weights in a local neighborhood. Based on this method, we also investigate possible feature combinations to calculate neighboring weights. We train on a colorized point cloud from the city of Hannover, Germany, and classify road points into 7 classes that reveal detailed functions, i.e., sidewalk, cycling path, rail track, parking area, motorway, green area, and island without traffic. Also, three feature combinations inside the LFA module are examined, including the geometric feature vector only, the geometric feature vector combined with additional features (e.g., color), and the geometric feature vector combined with local differences of additional features. We achieve the best overall accuracy (86.23%) and mean IoU (69.41%) by adopting the second and third combinations respectively, with additional features including Red, Green, Blue, and intensity. The evaluation results demonstrate the effectiveness of our method, but we also observe that different road types benefit the most from different feature settings.

scholarly journals Disturbance Analysis in the Classification of Objects Obtained from Urban LiDAR Point Clouds with Convolutional Neural Networks

2021 ◽  
Vol 13 (11) ◽  
pp. 2135
Author(s):  
Jesús Balado ◽  
Pedro Arias ◽  
Henrique Lorenzo ◽  
Adrián Meijide-Rodríguez
Keyword(s):  
Laser Scanning ◽  
Ambient Noise ◽  
Point Clouds ◽  
Density Variation ◽  
Density Reduction ◽  
Manual Intervention ◽  
Point Density ◽  
Disturbance Analysis ◽  
Street Furniture

Mobile Laser Scanning (MLS) systems have proven their usefulness in the rapid and accurate acquisition of the urban environment. From the generated point clouds, street furniture can be extracted and classified without manual intervention. However, this process of acquisition and classification is not error-free, caused mainly by disturbances. This paper analyses the effect of three disturbances (point density variation, ambient noise, and occlusions) on the classification of urban objects in point clouds. From point clouds acquired in real case studies, synthetic disturbances are generated and added. The point density reduction is generated by downsampling in a voxel-wise distribution. The ambient noise is generated as random points within the bounding box of the object, and the occlusion is generated by eliminating points contained in a sphere. Samples with disturbances are classified by a pre-trained Convolutional Neural Network (CNN). The results showed different behaviours for each disturbance: density reduction affected objects depending on the object shape and dimensions, ambient noise depending on the volume of the object, while occlusions depended on their size and location. Finally, the CNN was re-trained with a percentage of synthetic samples with disturbances. An improvement in the performance of 10–40% was reported except for occlusions with a radius larger than 1 m.

scholarly journals Linear-Based Incremental Co-Registration of MLS and Photogrammetric Point Clouds

2021 ◽  
Vol 13 (11) ◽  
pp. 2195
Author(s):  
Shiming Li ◽  
Xuming Ge ◽  
Shengfu Li ◽  
Bo Xu ◽  
Zhendong Wang
Keyword(s):  
Point Cloud ◽  
Laser Scanning ◽  
Point Clouds ◽  
Registration Method ◽  
Cloud Data ◽  
Linear Feature ◽  
Data Registration ◽  
Source Point ◽  
Urban Remote Sensing ◽  
Single Data

Today, mobile laser scanning and oblique photogrammetry are two standard urban remote sensing acquisition methods, and the cross-source point-cloud data obtained using these methods have significant differences and complementarity. Accurate co-registration can make up for the limitations of a single data source, but many existing registration methods face critical challenges. Therefore, in this paper, we propose a systematic incremental registration method that can successfully register MLS and photogrammetric point clouds in the presence of a large number of missing data, large variations in point density, and scale differences. The robustness of this method is due to its elimination of noise in the extracted linear features and its 2D incremental registration strategy. There are three main contributions of our work: (1) the development of an end-to-end automatic cross-source point-cloud registration method; (2) a way to effectively extract the linear feature and restore the scale; and (3) an incremental registration strategy that simplifies the complex registration process. The experimental results show that this method can successfully achieve cross-source data registration, while other methods have difficulty obtaining satisfactory registration results efficiently. Moreover, this method can be extended to more point-cloud sources.

Sign in / Sign up

Export Citation Format

Share Document