A Novel Octree-Based 3-D Fully Convolutional Neural Network for Point Cloud Classification in Road Environment

Xiang, Binbin; Tu, Jingmin; Yao, Jian; Li, Li

doi:10.1109/tgrs.2019.2916625

Cited by 19 publications

(11 citation statements)

References 49 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The maximum deviations for the two kinds of input conditions were 0.117 m and 0.230 m, respectively. The minimum variance was about 0.045 m, and most of the errors were controlled to within 0.1 m. 1 Horizontal and 2 elevation deviation of the first input condition, 4 horizontal and 5 elevation deviation of the second input condition. 3,6 Euclidean distance deviation of the first and second condition, respectively.…”

Section: Reconstructed Scanner Trackmentioning

confidence: 99%

“…Mobile laser scanning (MLS) systems collect a large number of three-dimensional (3D) road information along a vehicle's trajectory with high precision [1], and have been widely applied to base surveying [2], road and traffic engineering [3][4][5][6], urban planning and management [7], digital cities [8], forestry investigation [9], and cultural relics' protection [10]. Significant progress has been made in research on reconstructing scene models, extracting typical objects, and road surveys [11] based on MLS data.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Recovering Missing Trajectory Data for Mobile Laser Scanning Systems

et al. 2020

View full text Add to dashboard Cite

Trajectory data are often used as important auxiliary information in preprocessing and extracting the target from mobile laser scanning data. However, the trajectory data stored independently may be lost and destroyed for various reasons, making the data unavailable for the relevant models. This study proposes recovering the trajectory of the scanner from point cloud data following the scanning principles of a rotating mirror. Two approaches are proposed from different input conditions: Ordered three-dimensional coordinates of point cloud data, with and without acquisition time. We recovered the scanner’s ground track through road point density analysis and restored the position of the center of emission of the laser based on plane reconstruction on a single scanning line. The validity and reliability of the proposed approaches were verified in the four typical urban, rural, winding, and viaduct road environments using two systems from different manufacturers. The result deviations of the ground track and scanner trajectory from their actual position were a few centimeters and less than 1 decimeter, respectively. Such an error is sufficiently small for the trajectory data to be used in the relevant algorithms.

show abstract

Section: Reconstructed Scanner Trackmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Recovering Missing Trajectory Data for Mobile Laser Scanning Systems

et al. 2020

View full text Add to dashboard Cite

show abstract

“…It is not available for voxel-based modelling methods when using raster data. However, scholars have attempted to bring algorithms to enable topological relationship queries, such as Fully Convolutional Neutral Network (FCNN) (Xiang et al, 2019) and binary address encoding (Keling et al, 2017).…”

Section: Technical Requirementsmentioning

confidence: 99%

“…Mesh segmentation (Rouhani et al, 2017) Voxel 3D shape analysis (Xiang et al, 2019); 3D visualization (Vo et al, 2015) Wireframe Indoor reconstruction (Jung et al, 2016) B-rep 3D object visualisation (Massarwi and Elber, 2016) CSG Tree representation (Chen et al, 2017); 3Dsubsurface visualisation (Du et al, 2018) B-rep + CSG Data volume reduction (Ming et al, 2016) BIM Subway station risk control (Du et al, 2015); tunnel maintenance (Lee et al, 2018).…”

Section: Meshmentioning

confidence: 99%

Urban 3d Modelling Methods: A State-of-the-Art Review

Ying

Koeva

Kuffer

et al. 2020

Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

Abstract. As urbanisation accelerates, the urban landscape reshapes at a fast pace. Consequently, the urban built environment continuously evolves horizontally as well as vertically. However, more attention in the field of spatial analysis is given to horizontal dynamics, despite the importance of geoinformation in the vertical dimension. 3D modelling methods have gained popularity due to their powerful capability of capturing and analysing geoinformation in the vertical dimension and visualising objects lifelike in the urban built environment. Various urban applications with diverse 3D modelling methods at different research scales and purposes have emerged. However, there is no systematic overview of these different modelling methods. Therefore, it is imperative to provide an up-to-date review of these advances. In this paper, we aim to review urban 3D modelling methods widely used in the prior 5-year period (2015–2020). Our analysis focuses on five attributes, i.e., basic characteristics, data requirements, technical requirements, users requirements and ethical considerations. The discussion presents the current status of 3D modelling methods – a wide range of applications yet with substantial development potential. This paper closes with insights for future work regarding the necessities of 3D data structure support as well as interdisciplinary research, specifically for big data management and integration.

show abstract

“…Another approach is to use 3D CNNs on 3D voxels generated from the point cloud [5]- [10], [28]. Voxels divide the space into small uniform grids with values that could be binary, normal orientations, or density.…”

Section: Related Work a Object Classification Using Deep Neural mentioning

confidence: 99%

PL-Net3d: Robust 3D Object Class Recognition Using Geometric Models

et al. 2019

View full text Add to dashboard Cite

Three-dimensional point clouds produced by 3D scanners are often noisy and contain outliers. Such data inaccuracies can significantly affect current deep learning-based methods and reduce their ability to classify objects. Most deep neural networks-based object classification methods were targeted to achieve high classification accuracy without considering classification robustness. Thus, despite their great success, they still fail to achieve good classification accuracy with low levels of noise and outliers. This work is carried out to develop a robust network structure that can solidly identify objects. The proposed method uses patches of planar segments, which can robustly capture object appearance. The planar segments information are then fed into a deep neural network for classification. We base our approach on the PointNet deep learning architecture. Our method was tested against several kinds of data inaccuracies such as scattered outliers, clustered outliers, noise and missing points. The proposed method shows excellent performance in the presence of these inaccuracies compared to state-of-the-art techniques. By decomposing objects into planes, the suggested method is simple, fast, provides good classification accuracy and can handle different kinds of point cloud data inaccuracies. The code can be found at https://github.com/AymanMukh/Pl-Net3D INDEX TERMS Object recognition, point cloud classification, primitive fitting, robust classification.

show abstract

A Novel Octree-Based 3-D Fully Convolutional Neural Network for Point Cloud Classification in Road Environment

Cited by 19 publications

References 49 publications

Recovering Missing Trajectory Data for Mobile Laser Scanning Systems

Recovering Missing Trajectory Data for Mobile Laser Scanning Systems

Urban 3d Modelling Methods: A State-of-the-Art Review

PL-Net3d: Robust 3D Object Class Recognition Using Geometric Models

Contact Info

Product

Resources

About