scholarly journals ASSESSING LIDAR TRAINING DATA QUANTITIES FOR CLASSIFICATION MODELS

2021 ◽  
Vol XLVI-4/W4-2021 ◽  
pp. 101-106
Author(s):  
O. Majgaonkar ◽  
K. Panchal ◽  
D. Laefer ◽  
M. Stanley ◽  
Y. Zaki
Keyword(s):  
Point Cloud ◽  
Classification Performance ◽  
Training Data ◽  
Lidar Data ◽  
Data Sets ◽  
Classification Models ◽  
Fundamental Properties ◽  
Point Cloud Classification ◽  
The Impact ◽  
Insight Into

Abstract. Classifying objects within aerial Light Detection and Ranging (LiDAR) data is an essential task to which machine learning (ML) is applied increasingly. ML has been shown to be more effective on LiDAR than imagery for classification, but most efforts have focused on imagery because of the challenges presented by LiDAR data. LiDAR datasets are of higher dimensionality, discontinuous, heterogenous, spatially incomplete, and often scarce. As such, there has been little examination into the fundamental properties of the training data required for acceptable performance of classification models tailored for LiDAR data. The quantity of training data is one such crucial property, because training on different sizes of data provides insight into a model’s performance with differing data sets. This paper assesses the impact of training data size on the accuracy of PointNet, a widely used ML approach for point cloud classification. Subsets of ModelNet ranging from 40 to 9,843 objects were validated on a test set of 400 objects. Accuracy improved logarithmically; decelerating from 45 objects onwards, it slowed significantly at a training size of 2,000 objects, corresponding to 20,000,000 points. This work contributes to the theoretical foundation for development of LiDAR-focused models by establishing a learning curve, suggesting the minimum quantity of manually labelled data necessary for satisfactory classification performance and providing a path for further analysis of the effects of modifying training data characteristics.

scholarly journals PCCT: A POINT CLOUD CLASSIFICATION TOOL TO CREATE 3D TRAINING DATA TO ADJUST AND DEVELOP 3D CONVNET

2019 ◽  
Vol XLII-2/W16 ◽  
pp. 35-40
Author(s):  
E. Barnefske ◽  
H. Sternberg
Keyword(s):  
Network Architecture ◽  
Point Cloud ◽  
Three Dimensional ◽  
Point Clouds ◽  
Classification Performance ◽  
Training Data ◽  
Process Step ◽  
Camera Systems ◽  
Classification Tool ◽  
Point Cloud Classification

<p><strong>Abstract.</strong> Point clouds give a very detailed and sometimes very accurate representation of the geometry of captured objects. In surveying, point clouds captured with laser scanners or camera systems are an intermediate result that must be processed further. Often the point cloud has to be divided into regions of similar types (object classes) for the next process steps. These classifications are very time-consuming and cost-intensive compared to acquisition. In order to automate this process step, conventional neural networks (ConvNet), which take over the classification task, are investigated in detail. In addition to the network architecture, the classification performance of a ConvNet depends on the training data with which the task is learned. This paper presents and evaluates the point clould classification tool (PCCT) developed at HCU Hamburg. With the PCCT, large point cloud collections can be semi-automatically classified. Furthermore, the influence of erroneous points in three-dimensional point clouds is investigated. The network architecture PointNet is used for this investigation.</p>

scholarly journals 3-D Point Cloud Registration Using Convolutional Neural Networks

2019 ◽  
Vol 9 (16) ◽  
pp. 3273 ◽  
Author(s):  
Wen-Chung Chang ◽  
Van-Toan Pham
Keyword(s):  
Pose Estimation ◽  
Point Cloud ◽  
Full Range ◽  
Point Clouds ◽  
Fixed Time ◽  
Training Data ◽  
Data Sets ◽  
Point Cloud Registration ◽  
Cloud Data ◽  
Model Point

This paper develops a registration architecture for the purpose of estimating relative pose including the rotation and the translation of an object in terms of a model in 3-D space based on 3-D point clouds captured by a 3-D camera. Particularly, this paper addresses the time-consuming problem of 3-D point cloud registration which is essential for the closed-loop industrial automated assembly systems that demand fixed time for accurate pose estimation. Firstly, two different descriptors are developed in order to extract coarse and detailed features of these point cloud data sets for the purpose of creating training data sets according to diversified orientations. Secondly, in order to guarantee fast pose estimation in fixed time, a seemingly novel registration architecture by employing two consecutive convolutional neural network (CNN) models is proposed. After training, the proposed CNN architecture can estimate the rotation between the model point cloud and a data point cloud, followed by the translation estimation based on computing average values. By covering a smaller range of uncertainty of the orientation compared with a full range of uncertainty covered by the first CNN model, the second CNN model can precisely estimate the orientation of the 3-D point cloud. Finally, the performance of the algorithm proposed in this paper has been validated by experiments in comparison with baseline methods. Based on these results, the proposed algorithm significantly reduces the estimation time while maintaining high precision.

scholarly journals GEOMETRIC FEATURES AND THEIR RELEVANCE FOR 3D POINT CLOUD CLASSIFICATION

2017 ◽  
Vol IV-1/W1 ◽  
pp. 157-164 ◽  
Author(s):  
M. Weinmann ◽  
B. Jutzi ◽  
C. Mallet ◽  
M. Weinmann
Keyword(s):  
Influencing Factors ◽  
Point Cloud ◽  
Geometric Features ◽  
3D Point Cloud ◽  
Point Sampling ◽  
Cloud Data ◽  
Semantic Classes ◽  
Automatic Interpretation ◽  
Point Cloud Classification ◽  
The Impact

In this paper, we focus on the automatic interpretation of 3D point cloud data in terms of associating a class label to each 3D point. While much effort has recently been spent on this research topic, little attention has been paid to the influencing factors that affect the quality of the derived classification results. For this reason, we investigate fundamental influencing factors making geometric features more or less relevant with respect to the classification task. We present a framework which consists of five components addressing point sampling, neighborhood recovery, feature extraction, classification and feature relevance assessment. To analyze the impact of the main influencing factors which are represented by the given point sampling and the selected neighborhood type, we present the results derived with different configurations of our framework for a commonly used benchmark dataset for which a reference labeling with respect to three structural classes (<i>linear structures, planar structures</i> and <i>volumetric structures</i>) as well as a reference labeling with respect to five semantic classes (<i>Wire, Pole/Trunk, Façade, Ground</i> and <i>Vegetation</i>) is available.

scholarly journals COMPARISON OF TRADITIONAL AND MACHINE LEARNING BASE METHODS FOR GROUND POINT CLOUD LABELING

2019 ◽  
Vol XLII-4/W18 ◽  
pp. 141-145
Author(s):  
S. M. Ayazi ◽  
M. Saadat Seresht
Keyword(s):  
Machine Learning ◽  
Point Cloud ◽  
Type I Error ◽  
Total Error ◽  
Training Data ◽  
Lidar Data ◽  
Type I ◽  
Type Ii ◽  
Type Ii Error ◽  
Digital Photogrammetry

Abstract. Today, a variety of methods have been proposed by researchers to distinguish ground and non-ground points in point cloud data. Most fully automated methods have a common disadvantage which is the lack of proper algorithm response for all areas and levels of the ground, so most of these algorithms have good outcomes in simple landscapes but encounter problems in complex landscapes. Point cloud filtering techniques can be divided into two general rule-based and novel methods. Today, the use of machine learning techniques has improved the results of classification, which has led to significant results, especially when data can be labelled at the presence of training data. In this paper, firstly, altimeter and radiometric features are extracted from the LiDAR data and the point cloud derived from digital photogrammetry. Then, these features are participated in a classification process using SVM learning and random forest methods, and the ground and Non-ground points are classified. The classification results using this method on LiDAR data show a total error of 6.2%, a type I error of 5.4%, and a type II error of 13.2%. The comparison of the proposed method with the results of LASTools software shows a reduction in total error and type I error (while increasing the type II error). This method was also investigated on the dense point cloud obtained from digital photogrammetry and based on this study, the total was 7.2%, the type I error was 6.8%, and the type II error was 10.9%.

scholarly journals Multi-View Features Joint Learning with Label and Local Distribution Consistency for Point Cloud Classification

2020 ◽  
Vol 12 (1) ◽  
pp. 135
Author(s):  
Guofeng Tong ◽  
Yong Li ◽  
Dong Chen ◽  
Shaobo Xia ◽  
Jiju Peethambaran ◽  
...  
Keyword(s):  
Point Cloud ◽  
Feature Space ◽  
Ground Truth ◽  
Classification Performance ◽  
Local Distribution ◽  
Joint Learning ◽  
Linear Classifiers ◽  
Cloud Classification ◽  
Feature Projection ◽  
Point Cloud Classification

In outdoor Light Detection and Ranging (lidar)point cloud classification, finding the discriminative features for point cloud perception and scene understanding represents one of the great challenges. The features derived from defect-laden (i.e., noise, outliers, occlusions and irregularities) and raw outdoor LiDAR scans usually contain redundant and irrelevant information which adversely affects the accuracy of point semantic labeling. Moreover, point cloud features of different views have a capability to express different attributes of the same point. The simplest way of concatenating these features of different views cannot guarantee the applicability and effectiveness of the fused features. To solve these problems and achieve outdoor point cloud classification with fewer training samples, we propose a novel multi-view features and classifiers’ joint learning framework. The proposed framework uses label consistency and local distribution consistency of multi-space constraints for multi-view point cloud features extraction and classification. In the framework, the manifold learning is used to carry out subspace joint learning of multi-view features by introducing three kinds of constraints, i.e., local distribution consistency of feature space and position space, label consistency among multi-view predicted labels and ground truth, and label consistency among multi-view predicted labels. The proposed model can be well trained by fewer training points, and an iterative algorithm is used to solve the joint optimization of multi-view feature projection matrices and linear classifiers. Subsequently, the multi-view features are fused and used for point cloud classification effectively. We evaluate the proposed method on five different point cloud scenes and experimental results demonstrate that the classification performance of the proposed method is at par or outperforms the compared algorithms.

scholarly journals Geometry Sharing Network for 3D Point Cloud Classification and Segmentation

2020 ◽  
Vol 34 (07) ◽  
pp. 12500-12507 ◽  
Author(s):  
Mingye Xu ◽  
Zhipeng Zhou ◽  
Yu Qiao
Keyword(s):  
Point Cloud ◽  
State Of The Art ◽  
Nearest Neighbors ◽  
Classification Performance ◽  
3D Point Cloud ◽  
Geometric Information ◽  
Geometric Transformations ◽  
Geometry Similarity ◽  
Public Datasets ◽  
Point Cloud Classification

In spite of the recent progresses on classifying 3D point cloud with deep CNNs, large geometric transformations like rotation and translation remain challenging problem and harm the final classification performance. To address this challenge, we propose Geometry Sharing Network (GS-Net) which effectively learns point descriptors with holistic context to enhance the robustness to geometric transformations. Compared with previous 3D point CNNs which perform convolution on nearby points, GS-Net can aggregate point features in a more global way. Specially, GS-Net consists of Geometry Similarity Connection (GSC) modules which exploit Eigen-Graph to group distant points with similar and relevant geometric information, and aggregate features from nearest neighbors in both Euclidean space and Eigenvalue space. This design allows GS-Net to efficiently capture both local and holistic geometric features such as symmetry, curvature, convexity and connectivity. Theoretically, we show the nearest neighbors of each point in Eigenvalue space are invariant to rotation and translation. We conduct extensive experiments on public datasets, ModelNet40, ShapeNet Part. Experiments demonstrate that GS-Net achieves the state-of-the-art performances on major datasets, 93.3% on ModelNet40, and are more robust to geometric transformations.

scholarly journals GENERATING SYNTHETIC 3D POINT SEGMENTS FOR IMPROVED CLASSIFICATION OF MOBILE LIDAR POINT CLOUDS

2021 ◽  
Vol XLIII-B2-2021 ◽  
pp. 139-144
Author(s):  
S. A. Chitnis ◽  
Z. Huang ◽  
K. Khoshelham
Keyword(s):  
Semantic Information ◽  
State Of The Art ◽  
Point Clouds ◽  
Classification Performance ◽  
Training Data ◽  
Lidar Data ◽  
Real Point ◽  
The Road ◽  
Training Samples

Abstract. Mobile lidar point clouds are commonly used for 3d mapping of road environments as they provide a rich, highly detailed geometric representation of objects on and around the road. However, raw lidar point clouds lack semantic information about the type of objects, which is necessary for various applications. Existing methods for the classification of objects in mobile lidar data, including state of the art deep learning methods, achieve relatively low accuracies, and a primary reason for this under-performance is the inadequacy of available 3d training samples to sufficiently train deep networks. In this paper, we propose a generative model for creating synthetic 3d point segments that can aid in improving the classification performance of mobile lidar point clouds. We train a 3d Adversarial Autoencoder (3dAAE) to generate synthetic point segments that exhibit a high resemblance to and share similar geometric features with real point segments. We evaluate the performance of a PointNet-like classifier trained with and without the synthetic point segments. The evaluation results support our hypothesis that training a classifier with training data augmented with synthetic samples leads to significant improvement in the classification performance. Specifically, our model achieves an F1 score of 0.94 for vehicles and pedestrians and 1.00 for traffic signs.

scholarly journals Detection of Outliers in LiDAR Data Acquired by Multiple Platforms over Sorghum and Maize

2021 ◽  
Vol 13 (21) ◽  
pp. 4445
Author(s):  
Behrokh Nazeri ◽  
Melba Crawford
Keyword(s):  
Deep Learning ◽  
Outlier Detection ◽  
Point Cloud ◽  
Lidar Data ◽  
Point Cloud Data ◽  
Row Crops ◽  
Cloud Data ◽  
Local Point ◽  
Before And After ◽  
The Impact

High-resolution point cloud data acquired with a laser scanner from any platform contain random noise and outliers. Therefore, outlier detection in LiDAR data is often necessary prior to analysis. Applications in agriculture are particularly challenging, as there is typically no prior knowledge of the statistical distribution of points, plant complexity, and local point densities, which are crop-dependent. The goals of this study were first to investigate approaches to minimize the impact of outliers on LiDAR acquired over agricultural row crops, and specifically for sorghum and maize breeding experiments, by an unmanned aerial vehicle (UAV) and a wheel-based ground platform; second, to evaluate the impact of existing outliers in the datasets on leaf area index (LAI) prediction using LiDAR data. Two methods were investigated to detect and remove the outliers from the plant datasets. The first was based on surface fitting to noisy point cloud data via normal and curvature estimation in a local neighborhood. The second utilized the PointCleanNet deep learning framework. Both methods were applied to individual plants and field-based datasets. To evaluate the method, an F-score was calculated for synthetic data in the controlled conditions, and LAI, the variable being predicted, was computed both before and after outlier removal for both scenarios. Results indicate that the deep learning method for outlier detection is more robust than the geometric approach to changes in point densities, level of noise, and shapes. The prediction of LAI was also improved for the wheel-based vehicle data based on the coefficient of determination (R2) and the root mean squared error (RMSE) of the residuals before and after the removal of outliers.

Sign in / Sign up

Export Citation Format

Share Document