scholarly journals Identifying roadside objects in mobile laser scanning data using image-based point cloud segmentation

2020 ◽  
Vol 25 ◽  
pp. 545-560
Author(s):  
Gustaf Uggla ◽  
Milan Horemuz
Keyword(s):  
Point Cloud ◽  
Laser Scanning ◽  
Large Data ◽  
Semantic Segmentation ◽  
Point Clouds ◽  
Object Identification ◽  
Data Sets ◽  
Visual Appearance ◽  
Segmentation Of Images ◽  
Point Cloud Classification

Capturing geographic information from a mobile platform, a method known as mobile mapping, is today one of the best methods for rapid and safe data acquisition along roads and railroads. The digitalization of society and the use of information technology in the construction industry is increasing the need for structured geometric and semantic information about the built environment. This puts an emphasis on automatic object identification in data such as point clouds. Most point clouds are accompanied by RGB images, and a recent literature review showed that these are possibly underutilized for object identification. This article presents a method (image-based point cloud segmentations – IBPCS) where semantic segmentation of images is used to filter point clouds, which drastically reduces the number of points that have to be considered in object identification and allows simpler algorithms to be used. An example implementation where IBPCS is used to identify roadside game fences along a country road is provided, and the accuracy and efficiency of the method is compared to the performance of PointNet, which is a neural network designed for end-to-end point cloud classification and segmentation. The results show that our implementation of IBPCS outperforms PointNet for the given task. The strengths of IBPCS are the ability to filter point clouds based on visual appearance and that it efficiently can process large data sets. This makes the method a suitable candidate for object identification along rural roads and railroads, where the objects of interest are scattered over long distances.

scholarly journals GEOMETRY-BASED POINT CLOUD CLASSIFICATION USING HEIGHT DISTRIBUTIONS

2020 ◽  
Vol V-2-2020 ◽  
pp. 259-266
Author(s):  
F. Politz ◽  
M. Sester ◽  
C. Brenner
Keyword(s):  
Point Cloud ◽  
Laser Scanning ◽  
Ground Level ◽  
Semantic Segmentation ◽  
Point Clouds ◽  
Training Data ◽  
Mountainous Regions ◽  
Dense Image ◽  
The Mean ◽  
Point Cloud Classification

Abstract. Semantic segmentation is one of the main steps in the processing chain for Airborne Laser Scanning (ALS) point clouds, but it is also one of the most labour intensive steps, as it requires many labelled examples to train a classifier. National mapping agencies (NMAs) have to acquire nationwide ALS data every couple of years for their duties. Having point clouds cover different terrains such as flat or mountainous regions, a classifier often requires a refinement using additional data from those specific terrains. In this study, we present an algorithm, which is able to classify point clouds of similar terrain types without requiring any additional training data and which is still able to achieve overall F1-Scores of over 90% in most setups. Our algorithm uses up to two height distributions within a single cell in a rasterized point cloud. For each distribution, the empirical mean and standard deviation are calculated, which are the input for a Convolutional Neural Network (CNN) classifier. Consequently, our approach only requires the geometry of point clouds, which enables also the usage of the same network structure for point clouds from other sensor systems such as Dense Image Matching. Since the mean ground level varies with the observed area, we also examined five different normalisation methods for our input in order to reduce the ground influence on the point clouds and thus increase its transferability towards other datasets. We test our trained networks on four different tests sets with the classes’ ground, building, water, non-ground and bridge.

scholarly journals EXPLORING ALS AND DIM DATA FOR SEMANTIC SEGMENTATION USING CNNS

2018 ◽  
Vol XLII-1 ◽  
pp. 347-354 ◽  
Author(s):  
F. Politz ◽  
M. Sester
Keyword(s):  
Point Cloud ◽  
Laser Scanning ◽  
Semantic Segmentation ◽  
Point Clouds ◽  
Good Alternative ◽  
Aerial Images ◽  
Learning Approaches ◽  
Advantages And Disadvantages ◽  
Sensing Applications ◽  
High Level

<p><strong>Abstract.</strong> Over the past years, the algorithms for dense image matching (DIM) to obtain point clouds from aerial images improved significantly. Consequently, DIM point clouds are now a good alternative to the established Airborne Laser Scanning (ALS) point clouds for remote sensing applications. In order to derive high-level applications such as digital terrain models or city models, each point within a point cloud must be assigned a class label. Usually, ALS and DIM are labelled with different classifiers due to their varying characteristics. In this work, we explore both point cloud types in a fully convolutional encoder-decoder network, which learns to classify ALS as well as DIM point clouds. As input, we project the point clouds onto a 2D image raster plane and calculate the minimal, average and maximal height values for each raster cell. The network then differentiates between the classes ground, non-ground, building and no data. We test our network in six training setups using only one point cloud type, both point clouds as well as several transfer-learning approaches. We quantitatively and qualitatively compare all results and discuss the advantages and disadvantages of all setups. The best network achieves an overall accuracy of 96<span class="thinspace"></span>% in an ALS and 83<span class="thinspace"></span>% in a DIM test set.</p>

scholarly journals UNDERSTANDING 3D POINT CLOUD DEEP NEURAL NETWORKS BY VISUALIZATION TECHNIQUES

2020 ◽  
Vol XLIII-B2-2020 ◽  
pp. 651-657
Author(s):  
Y. Cao ◽  
M. Previtali ◽  
M. Scaioni
Keyword(s):  
Point Cloud ◽  
Semantic Segmentation ◽  
Point Clouds ◽  
Learning Networks ◽  
Quantitative Investigation ◽  
Different Types ◽  
Visualization Techniques ◽  
Point Cloud Classification ◽  
Learned Features ◽  
Excellent Tool

Abstract. In the wake of the success of Deep Learning Networks (DLN) for image recognition, object detection, shape classification and semantic segmentation, this approach has proven to be both a major breakthrough and an excellent tool in point cloud classification. However, understanding how different types of DLN achieve still lacks. In several studies the output of segmentation/classification process is compared against benchmarks, but the network is treated as a “black-box” and intermediate steps are not deeply analysed. Specifically, here the following questions are discussed: (1) what exactly did DLN learn from a point cloud? (2) On the basis of what information do DLN make decisions? To conduct such a quantitative investigation of these DLN applied to point clouds, this paper investigates the visual interpretability for the decision-making process. Firstly, we introduce a reconstruction network able to reconstruct and visualise the learned features, in order to face with question (1). Then, we propose 3DCAM to indicate the discriminative point cloud regions used by these networks to identify that category, thus dealing with question (2). Through answering the above two questions, the paper would like to offer some initial solutions to better understand the application of DLN to point clouds.

scholarly journals Virtual Disassembling of Historical Edifices: Experiments and Assessments of an Automatic Approach for Classifying Multi-Scalar Point Clouds into Architectural Elements

Sensors ◽  
2020 ◽  
Vol 20 (8) ◽  
pp. 2161 ◽  
Author(s):  
Arnadi Murtiyoso ◽  
Pierre Grussenmeyer
Keyword(s):  
Point Cloud ◽  
Laser Scanning ◽  
Semantic Annotation ◽  
Semantic Segmentation ◽  
Point Clouds ◽  
Training Data ◽  
Algorithmic Approach ◽  
Architectural Elements ◽  
Semantic Labeling ◽  
Geometric Point

3D heritage documentation has seen a surge in the past decade due to developments in reality-based 3D recording techniques. Several methods such as photogrammetry and laser scanning are becoming ubiquitous amongst architects, archaeologists, surveyors, and conservators. The main result of these methods is a 3D representation of the object in the form of point clouds. However, a solely geometric point cloud is often insufficient for further analysis, monitoring, and model predicting of the heritage object. The semantic annotation of point clouds remains an interesting research topic since traditionally it requires manual labeling and therefore a lot of time and resources. This paper proposes an automated pipeline to segment and classify multi-scalar point clouds in the case of heritage object. This is done in order to perform multi-level segmentation from the scale of a historical neighborhood up until that of architectural elements, specifically pillars and beams. The proposed workflow involves an algorithmic approach in the form of a toolbox which includes various functions covering the semantic segmentation of large point clouds into smaller, more manageable and semantically labeled clusters. The first part of the workflow will explain the segmentation and semantic labeling of heritage complexes into individual buildings, while a second part will discuss the use of the same toolbox to segment the resulting buildings further into architectural elements. The toolbox was tested on several historical buildings and showed promising results. The ultimate intention of the project is to help the manual point cloud labeling, especially when confronted with the large training data requirements of machine learning-based algorithms.

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.

scholarly journals SEMANTIC SEGMENTATION OF MOBILE LASER SCANNING POINT CLOUDS WITH LONG SHORT-TERM MEMORY NETWORKS: PRELIMINARY RESULTS

2021 ◽  
Vol XLIII-B2-2021 ◽  
pp. 123-130
Author(s):  
J. Balado ◽  
P. van Oosterom ◽  
L. Díaz-Vilariño ◽  
P. Arias
Keyword(s):  
Point Cloud ◽  
Laser Scanning ◽  
Short Term Memory ◽  
Semantic Segmentation ◽  
Point Clouds ◽  
Time Signal ◽  
Success Rates ◽  
Short Term ◽  
Term Memory ◽  
Long Short Term Memory

Abstract. Although point clouds are characterized as a type of unstructured data, timestamp attribute can structure point clouds into scanlines and shape them into a time signal. The present work studies the transformation of the street point cloud into a time signal based on the Z component for the semantic segmentation using Long Short-Term Memory (LSTM) networks. The experiment was conducted on the point cloud of a real case study. Several training sessions were performed changing the Level of Detail of the classification (coarse level with 3 classes and fine level with 11 classes), two levels of network depth and the use of weighting for the improvement of classes with low number of points. The results showed high accuracy, reaching at best 97.3% in the classification with 3 classes (ground, buildings, and objects) and 95.7% with 11 classes. The distribution of the success rates was not the same for all classes. The classes with the highest number of points obtained better results than the others. The application of weighting improved the classes with few points at the expense of the classes with more points. Increasing the number of hidden layers was shown as a preferable alternative to weighting. Given the high success rates and a behaviour of the LSTM consistent with other Neural Networks in point cloud processing, it is concluded that the LSTM is a feasible alternative for the semantic segmentation of point clouds transformed into time signals.

scholarly journals INVESTIGATIONS INTO THE QUALITY OF IMAGE-BASED POINT CLOUDS FROM UAV IMAGERY

2019 ◽  
Vol XLII-2/W13 ◽  
pp. 539-545 ◽  
Author(s):  
H.-J. Przybilla ◽  
M. Lindstaedt ◽  
T. Kersten
Keyword(s):  
Point Cloud ◽  
Laser Scanning ◽  
Image Data ◽  
Point Clouds ◽  
Data Sets ◽  
Test Field ◽  
Data Format ◽  
Software Packages ◽  
Dense Point

<p><strong>Abstract.</strong> The quality of image-based point clouds generated from images of UAV aerial flights is subject to various influencing factors. In addition to the performance of the sensor used (a digital camera), the image data format (e.g. TIF or JPG) is another important quality parameter. At the UAV test field at the former Zollern colliery (Dortmund, Germany), set up by Bochum University of Applied Sciences, a medium-format camera from Phase One (IXU 1000) was used to capture UAV image data in RAW format. This investigation aims at evaluating the influence of the image data format on point clouds generated by a Dense Image Matching process. Furthermore, the effects of different data filters, which are part of the evaluation programs, were considered. The processing was carried out with two software packages from Agisoft and Pix4D on the basis of both generated TIF or JPG data sets. The point clouds generated are the basis for the investigation presented in this contribution. Point cloud comparisons with reference data from terrestrial laser scanning were performed on selected test areas representing object-typical surfaces (with varying surface structures). In addition to these area-based comparisons, selected linear objects (profiles) were evaluated between the different data sets. Furthermore, height point deviations from the dense point clouds were determined using check points. Differences in the results generated through the two software packages used could be detected. The reasons for these differences are filtering settings used for the generation of dense point clouds. It can also be assumed that there are differences in the algorithms for point cloud generation which are implemented in the two software packages. The slightly compressed JPG image data used for the point cloud generation did not show any significant changes in the quality of the examined point clouds compared to the uncompressed TIF data sets.</p>

scholarly journals Point Set Multi-Level Aggregation Feature Extraction Based on Multi-Scale Max Pooling and LDA for Point Cloud Classification

2019 ◽  
Vol 11 (23) ◽  
pp. 2846 ◽  
Author(s):  
Tong ◽  
Li ◽  
Zhang ◽  
Chen ◽  
Zhang ◽  
...  
Keyword(s):  
Point Cloud ◽  
Laser Scanning ◽  
Single Point ◽  
Point Clouds ◽  
Max Pooling ◽  
Multi Scale ◽  
Cloud Classification ◽  
Point Set ◽  
Multi Level ◽  
Point Cloud Classification

Accurate and effective classification of lidar point clouds with discriminative features expression is a challenging task for scene understanding. In order to improve the accuracy and the robustness of point cloud classification based on single point features, we propose a novel point set multi-level aggregation features extraction and fusion method based on multi-scale max pooling and latent Dirichlet allocation (LDA). To this end, in the hierarchical point set feature extraction, point sets of different levels and sizes are first adaptively generated through multi-level clustering. Then, more effective sparse representation is implemented by locality-constrained linear coding (LLC) based on single point features, which contributes to the extraction of discriminative individual point set features. Next, the local point set features are extracted by combining the max pooling method and the multi-scale pyramid structure constructed by the point’s coordinates within each point set. The global and the local features of the point sets are effectively expressed by the fusion of multi-scale max pooling features and global features constructed by the point set LLC-LDA model. The point clouds are classified by using the point set multi-level aggregation features. Our experiments on two scenes of airborne laser scanning (ALS) point clouds—a mobile laser scanning (MLS) scene point cloud and a terrestrial laser scanning (TLS) scene point cloud—demonstrate the effectiveness of the proposed point set multi-level aggregation features for point cloud classification, and the proposed method outperforms other related and compared algorithms.

scholarly journals AUTOMATED BIM ENTITY RECONSTRUCTION FROM UNSTRUCTURED 3D POINTCLOUDS

2021 ◽  
Vol 30 ◽  
pp. 126-130
Author(s):  
Jan Voříšek ◽  
Bořek Patzák ◽  
Edita Dvořáková ◽  
Daniel Rypl
Keyword(s):  
Point Cloud ◽  
Laser Scanning ◽  
Point Clouds ◽  
Human Interaction ◽  
Data Sets ◽  
Building Projects ◽  
Cloud Data ◽  
Data Points ◽  
Floor Plans ◽  
Large Building

Laser scanning is used widely in architecture and construction to document existing buildings by providing accurate data for creating a 3D model. The output is a set of data points in space, so-called point cloud. While point clouds can be directly rendered and inspected, they do not hold any semantics. Typically, engineers manually obtain floor plans, structural models, or the whole BIM model, which is a very time-consuming task for large building projects. In this contribution, we present the design and concept of a PointCloud2BIM library [1]. It provides a set of algorithms for automated or user assisted detection of fundamental entities from scanned point cloud data sets, such as floors, rooms, walls, and openings, and identification of the mutual relationships between them. The entity detection is based on a reasonable degree of human interaction (i.e., expected wall thickness). The results reside in a platform-agnostic JSON database allowing future integration into any existing BIM software.

scholarly journals An Efficient Framework for Mobile Lidar Trajectory Reconstruction and Mo-norvana Segmentation

2019 ◽  
Vol 11 (7) ◽  
pp. 836 ◽  
Author(s):  
Erzhuo Che ◽  
Michael Olsen
Keyword(s):  
Point Cloud ◽  
Laser Scanning ◽  
Grid Point ◽  
Large Data ◽  
Point Clouds ◽  
Normal Variation ◽  
Variation Analysis ◽  
Cloud Data ◽  
Trajectory Reconstruction ◽  
Scan Pattern

Mobile laser scanning (MLS, or mobile lidar) is a 3-D data acquisition technique that has been widely used in a variety of applications in recent years due to its high accuracy and efficiency. However, given the large data volume and complexity of the point clouds, processing MLS data can be still challenging with respect to effectiveness, efficiency, and versatility. This paper proposes an efficient MLS data processing framework for general purposes consisting of three main steps: trajectory reconstruction, scan pattern grid generation, and Mo-norvana (Mobile Normal Variation Analysis) segmentation. We present a novel approach to reconstructing the scanner trajectory, which can then be used to structure the point cloud data into a scan pattern grid. By exploiting the scan pattern grid, point cloud segmentation can be performed using Mo-norvana, which is developed based on our previous work for processing Terrestrial Laser Scanning (TLS) data, normal variation analysis (Norvana). In this work, with an unorganized MLS point cloud as input, the proposed framework can complete various tasks that may be desired in many applications including trajectory reconstruction, data structuring, data visualization, edge detection, feature extraction, normal estimation, and segmentation. The performance of the proposed procedures are experimentally evaluated both qualitatively and quantitatively using multiple MLS datasets via the results of trajectory reconstruction, visualization, and segmentation. The efficiency of the proposed method is demonstrated to be able to handle a large dataset stably with a fast computation speed (about 1 million pts/sec. with 8 threads) by taking advantage of parallel programming.

Sign in / Sign up

Export Citation Format

Share Document