scholarly journals Coarse-to-Fine Classification of Road Infrastructure Elements from Mobile Point Clouds Using Symmetric Ensemble Point Network and Euclidean Cluster Extraction

Sensors ◽  
2019 ◽  
Vol 20 (1) ◽  
pp. 225 ◽  
Author(s):  
Duo Wang ◽  
Jin Wang ◽  
Marco Scaioni ◽  
Qi Si
Keyword(s):  
Deep Learning ◽  
Asset Management ◽  
Laser Scanning ◽  
Transportation Network ◽  
Point Clouds ◽  
Structural Features ◽  
Learning Networks ◽  
Clustering Methods ◽  
Multiple Objects ◽  
Road Infrastructure

Classifying point clouds obtained from mobile laser scanning of road environments is a fundamental yet challenging problem for road asset management and unmanned vehicle navigation. Deep learning networks need no prior knowledge to classify multiple objects, but often generate a certain amount of false predictions. However, traditional clustering methods often involve leveraging a priori knowledge, but may lack generalisability compared to deep learning networks. This paper presents a classification method that coarsely classifies multiple objects of road infrastructure with a symmetric ensemble point (SEP) network and then refines the results with a Euclidean cluster extraction (ECE) algorithm. The SEP network applies a symmetric function to capture relevant structural features at different scales and select optimal sub-samples using an ensemble method. The ECE subsequently adjusts points that have been predicted incorrectly by the first step. The experimental results indicate that this method effectively extracts six types of road infrastructure elements: road surfaces, buildings, walls, traffic signs, trees and streetlights. The overall accuracy of the SEP-ECE method improves by 3.97% with respect to PointNet. The achieved average classification accuracy is approximately 99.74 % , which is suitable for practical use in transportation network management.

scholarly journals DEM Extraction from ALS Point Clouds in Forest Areas via Graph Convolution Network

2020 ◽  
Vol 12 (1) ◽  
pp. 178 ◽  
Author(s):  
Jinming Zhang ◽  
Xiangyun Hu ◽  
Hengming Dai ◽  
ShenRun Qu
Keyword(s):  
Deep Learning ◽  
Point Cloud ◽  
Laser Scanning ◽  
Large Scale ◽  
Spatial Relationship ◽  
Point Clouds ◽  
Current Data ◽  
Data Sampling ◽  
Dynamic Graph ◽  
Convolution Model

It is difficult to extract a digital elevation model (DEM) from an airborne laser scanning (ALS) point cloud in a forest area because of the irregular and uneven distribution of ground and vegetation points. Machine learning, especially deep learning methods, has shown powerful feature extraction in accomplishing point cloud classification. However, most of the existing deep learning frameworks, such as PointNet, dynamic graph convolutional neural network (DGCNN), and SparseConvNet, cannot consider the particularity of ALS point clouds. For large-scene laser point clouds, the current data preprocessing methods are mostly based on random sampling, which is not suitable for DEM extraction tasks. In this study, we propose a novel data sampling algorithm for the data preparation of patch-based training and classification named T-Sampling. T-Sampling uses the set of the lowest points in a certain area as basic points with other points added to supplement it, which can guarantee the integrity of the terrain in the sampling area. In the learning part, we propose a new convolution model based on terrain named Tin-EdgeConv that fully considers the spatial relationship between ground and non-ground points when constructing a directed graph. We design a new network based on Tin-EdgeConv to extract local features and use PointNet architecture to extract global context information. Finally, we combine this information effectively with a designed attention fusion module. These aspects are important in achieving high classification accuracy. We evaluate the proposed method by using large-scale data from forest areas. Results show that our method is more accurate than existing algorithms.

scholarly journals Comparing Machine and Deep Learning Methods for Large 3D Heritage Semantic Segmentation

2020 ◽  
Vol 9 (9) ◽  
pp. 535
Author(s):  
Francesca Matrone ◽  
Eleonora Grilli ◽  
Massimo Martini ◽  
Marina Paolanti ◽  
Roberto Pierdicca ◽  
...  
Keyword(s):  
Deep Learning ◽  
Cultural Heritage ◽  
Laser Scanning ◽  
Semantic Segmentation ◽  
Point Clouds ◽  
Classification Algorithms ◽  
Learning Methods ◽  
3D Point Clouds ◽  
The Subject

In recent years semantic segmentation of 3D point clouds has been an argument that involves different fields of application. Cultural heritage scenarios have become the subject of this study mainly thanks to the development of photogrammetry and laser scanning techniques. Classification algorithms based on machine and deep learning methods allow to process huge amounts of data as 3D point clouds. In this context, the aim of this paper is to make a comparison between machine and deep learning methods for large 3D cultural heritage classification. Then, considering the best performances of both techniques, it proposes an architecture named DGCNN-Mod+3Dfeat that combines the positive aspects and advantages of these two methodologies for semantic segmentation of cultural heritage point clouds. To demonstrate the validity of our idea, several experiments from the ArCH benchmark are reported and commented.

scholarly journals An Adaptive End-to-End Classification Approach for Mobile Laser Scanning Point Clouds Based on Knowledge in Urban Scenes

2019 ◽  
Vol 11 (2) ◽  
pp. 186 ◽  
Author(s):  
Mingxue Zheng ◽  
Huayi Wu ◽  
Yong Li
Keyword(s):  
Laser Scanning ◽  
Point Clouds ◽  
Basic Knowledge ◽  
Multiple Objects ◽  
Urban Scenes ◽  
Knowledge Based ◽  
Training Samples ◽  
End To End ◽  
Heavy Training

It is fundamental for 3D city maps to efficiently classify objects of point clouds in urban scenes. However, it is still a large challenge to obtain massive training samples for point clouds and to sustain the huge training burden. To overcome it, a knowledge-based approach is proposed. The knowledge-based approach can explore discriminating features of objects based on people’s understanding of the surrounding environment, which exactly replaces the role of training samples. To implement the approach, a two-step segmentation procedure is carried out in this paper. In particular, Fourier Fitting is applied for second adaptive segmentation to separate points of multiple objects lying within a single group of the first segmentation. Then height difference and three geometrical eigen-features are extracted. In comparison to common classification methods, which need massive training samples, only basic knowledge of objects in urban scenes is needed to build an end-to-end match between objects and extracted features in the proposed approach. In addition, the proposed approach has high computational efficiency because of no heavy training process. Qualitative and quantificational experimental results show the proposed approach has promising performance for object classification in various urban scenes.

scholarly journals AN EFFICIENT DEEP LEARNING APPROACH FOR GROUND POINT FILTERING IN AERIAL LASER SCANNING POINT CLOUDS

2021 ◽  
Vol XLIII-B1-2021 ◽  
pp. 31-38
Author(s):  
A. Nurunnabi ◽  
F. N. Teferle ◽  
J. Li ◽  
R. C. Lindenbergh ◽  
A. Hunegnaw
Keyword(s):  
Deep Learning ◽  
Point Cloud ◽  
Laser Scanning ◽  
Three Dimensional ◽  
Ground Surface ◽  
Point Clouds ◽  
Urban Environments ◽  
Training Data ◽  
Ground Point ◽  
End To End

Abstract. Ground surface extraction is one of the classic tasks in airborne laser scanning (ALS) point cloud processing that is used for three-dimensional (3D) city modelling, infrastructure health monitoring, and disaster management. Many methods have been developed over the last three decades. Recently, Deep Learning (DL) has become the most dominant technique for 3D point cloud classification. DL methods used for classification can be categorized into end-to-end and non end-to-end approaches. One of the main challenges of using supervised DL approaches is getting a sufficient amount of training data. The main advantage of using a supervised non end-to-end approach is that it requires less training data. This paper introduces a novel local feature-based non end-to-end DL algorithm that generates a binary classifier for ground point filtering. It studies feature relevance, and investigates three models that are different combinations of features. This method is free from the limitations of point clouds’ irregular data structure and varying data density, which is the biggest challenge for using the elegant convolutional neural network. The new algorithm does not require transforming data into regular 3D voxel grids or any rasterization. The performance of the new method has been demonstrated through two ALS datasets covering urban environments. The method successfully labels ground and non-ground points in the presence of steep slopes and height discontinuity in the terrain. Experiments in this paper show that the algorithm achieves around 97% in both F1-score and model accuracy for ground point labelling.

scholarly journals Structure-Aware Convolution for 3D Point Cloud Classification and Segmentation

2020 ◽  
Vol 12 (4) ◽  
pp. 634 ◽  
Author(s):  
Lei Wang ◽  
Yuxuan Liu ◽  
Shenman Zhang ◽  
Jixing Yan ◽  
Pengjie Tao
Keyword(s):  
Deep Learning ◽  
Template Matching ◽  
Point Cloud ◽  
Structure Learning ◽  
Feature Learning ◽  
Point Clouds ◽  
Learning Networks ◽  
Geometric Structures ◽  
Learning Capability ◽  
3D Point Clouds

Semantic feature learning on 3D point clouds is quite challenging because of their irregular and unordered data structure. In this paper, we propose a novel structure-aware convolution (SAC) to generalize deep learning on regular grids to irregular 3D point clouds. Similar to the template-matching process of convolution on 2D images, the key of our SAC is to match the point clouds’ neighborhoods with a series of 3D kernels, where each kernel can be regarded as a “geometric template” formed by a set of learnable 3D points. Thus, the interested geometric structures of the input point clouds can be activated by the corresponding kernels. To verify the effectiveness of the proposed SAC, we embedded it into three recently developed point cloud deep learning networks (PointNet, PointNet++, and KCNet) as a lightweight module, and evaluated its performance on both classification and segmentation tasks. Experimental results show that, benefiting from the geometric structure learning capability of our SAC, all these back-end networks achieved better classification and segmentation performance (e.g., +2.77% mean accuracy for classification and +4.99% mean intersection over union (IoU) for segmentation) with few additional parameters. Furthermore, results also demonstrate that the proposed SAC is helpful in improving the robustness of networks with the constraints of geometric structures.

scholarly journals VB-Net: Voxel-Based Broad Learning Network for 3D Object Classification

2020 ◽  
Vol 10 (19) ◽  
pp. 6735 ◽  
Author(s):  
Zishu Liu ◽  
Wei Song ◽  
Yifei Tian ◽  
Sumi Ji ◽  
Yunsick Sung ◽  
...  
Keyword(s):  
Deep Learning ◽  
Three Dimensional ◽  
Object Classification ◽  
Point Clouds ◽  
Learning System ◽  
Learning Networks ◽  
3D Object ◽  
Feature Extractor ◽  
Irregular Point ◽  
3D Object Classification

Point clouds have been widely used in three-dimensional (3D) object classification tasks, i.e., people recognition in unmanned ground vehicles. However, the irregular data format of point clouds and the large number of parameters in deep learning networks affect the performance of object classification. This paper develops a 3D object classification system using a broad learning system (BLS) with a feature extractor called VB-Net. First, raw point clouds are voxelized into voxels. Through this step, irregular point clouds are converted into regular voxels which are easily processed by the feature extractor. Then, a pre-trained VoxNet is employed as a feature extractor to extract features from voxels. Finally, those features are used for object classification by the applied BLS. The proposed system is tested on the ModelNet40 dataset and ModelNet10 dataset. The average recognition accuracy was 83.99% and 90.08%, respectively. Compared to deep learning networks, the time consumption of the proposed system is significantly decreased.

scholarly journals POINTNET FOR THE AUTOMATIC CLASSIFICATION OF AERIAL POINT CLOUDS

2019 ◽  
Vol IV-2/W5 ◽  
pp. 445-452 ◽  
Author(s):  
M. Soilán ◽  
R. Lindenbergh ◽  
B. Riveiro ◽  
A. Sánchez-Rodríguez
Keyword(s):  
Deep Learning ◽  
Laser Scanning ◽  
False Negative ◽  
Semantic Segmentation ◽  
Point Clouds ◽  
Study Data ◽  
Classification Model ◽  
Ground Vegetation ◽  
Cloud Data

<p><strong>Abstract.</strong> During the last couple of years, there has been an increased interest to develop new deep learning networks specifically for processing 3D point cloud data. In that context, this work intends to expand the applicability of one of these networks, PointNet, from the semantic segmentation of indoor scenes, to outdoor point clouds acquired with Airborne Laser Scanning (ALS) systems. Our goal is to of assist the classification of future iterations of a national wide dataset such as the <i>Actueel Hoogtebestand Nederland</i> (AHN), using a classification model trained with a previous iteration. First, a simple application such as ground classification is proposed in order to prove the capabilities of the proposed deep learning architecture to perform an efficient point-wise classification with aerial point clouds. Then, two different models based on PointNet are defined to classify the most relevant elements in the case study data: Ground, vegetation and buildings. While the model for ground classification performs with a F-score metric above 96%, motivating the second part of the work, the overall accuracy of the remaining models is around 87%, showing consistency across different versions of AHN but with improvable false positive and false negative rates. Therefore, this work concludes that the proposed classification of future AHN iterations is feasible but needs more experimentation.</p>

scholarly journals Extraction of linear structures from digital terrain models using deep learning

2021 ◽  
Vol 2 ◽  
pp. 1-14
Author(s):  
Ramish Satari ◽  
Bashir Kazimi ◽  
Monika Sester
Keyword(s):  
Neural Networks ◽  
Deep Learning ◽  
Laser Scanning ◽  
Semantic Segmentation ◽  
Point Clouds ◽  
Linear Structures ◽  
Digital Terrain Models ◽  
Deep Convolutional Neural Networks ◽  
Digital Terrain ◽  
Terrain Models

Abstract. This paper explores the role deep convolutional neural networks play in automated extraction of linear structures using semantic segmentation techniques in Digital Terrain Models (DTMs). DTM is a regularly gridded raster created from laser scanning point clouds and represents elevations of the bare earth surface with respect to a reference. Recent advances in Deep Learning (DL) have made it possible to explore the use of semantic segmentation for detection of terrain structures in DTMs. This research examines two novel and practical deep convolutional neural network architectures i.e. an encoder-decoder network named as SegNet and the recent state-of-the-art high-resolution network (HRNet). This paper initially focuses on the pixel-wise binary classification in order to validate the applicability of the proposed approaches. The networks are trained to distinguish between points belonging to linear structures and those belonging to background. In the second step, multi-class segmentation is carried out on the same DTM dataset. The model is trained to not only detect a linear feature, but also to categorize it as one of the classes: hollow ways, roads, forest paths, historical paths, and streams. Results of the experiment in addition to the quantitative and qualitative analysis show the applicability of deep neural networks for detection of terrain structures in DTMs. From the deep learning models utilized, HRNet gives better results.

Sign in / Sign up

Export Citation Format

Share Document