Robust Normal Estimation for 3D LiDAR Point Clouds in Urban Environments

Zhao, Ran; Pang, Mingyong; Liu, Caixia; Zhang, Yanling

doi:10.3390/s19051248

Cited by 22 publications

(10 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Researchers in reference [5] introduced a point cloud segmentation method for urban environment data. Their method is based on the robust normal estimation by the construction of an octree-based hierarchical representation for input data.…”

Section: Related Workmentioning

confidence: 99%

Advanced Methods for Point Cloud Processing and Simplification

et al. 2020

View full text Add to dashboard Cite

Nowadays, mobile robot exploration needs a rangefinder to obtain a large number of measurement points to achieve a detailed and precise description of a surrounding area and objects, which is called the point cloud. However, a single point cloud scan does not cover the whole area, so multiple point cloud scans must be acquired and compared together to find the right matching between them in a process called registration method. This method requires further processing and places high demands on memory consumption, especially for small embedded devices in mobile robots. This paper describes a novel method to reduce the burden of processing for multiple point cloud scans. We introduce our approach to preprocess an input point cloud in order to detect planar surfaces, simplify space description, fill gaps in point clouds, and get important space features. All of these processes are achieved by applying advanced image processing methods in combination with the quantization of physical space points. The results show the reliability of our approach to detect close parallel walls with suitable parameter settings. More importantly, planar surface detection shows a 99% decrease in necessary descriptive points almost in all cases. This proposed approach is verified on the real indoor point clouds.

show abstract

Section: Related Workmentioning

confidence: 99%

Advanced Methods for Point Cloud Processing and Simplification

et al. 2020

View full text Add to dashboard Cite

show abstract

“…Normal estimation is one of the basic stages in 3D point cloud processing. Regression-based normal estimation is first done with the assumption that the surface of an object is smooth (continuous) throughout its surface, and the points around each point on the surface can be approached well by a plane (Zhao et al, 2019). Normal estimation is done to obtain a normal vector at each input data point.…”

Section: Normal Estimationmentioning

confidence: 99%

Polyfit Assisted Monoscopic Multi-Image Measurement Systems

Suwardhi

Trisyanti

Kamal

et al. 2019

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

View full text Add to dashboard Cite

Abstract. Nowadays, in light of the latest development in three-dimensional (3D) modeling technology, an essential role is given to the research and development of fully-automated or semi-automated processes in order to increase workflow effectiveness. A key challenge is thus to automate the process leading to the geometric model which supports the Building Information Modeling (BIM) or 3D-Geographical Information Systems (3D-GIS). This 3D model usually originates from image-based or range-based point clouds. This research is the beginning of the development of a 3D modeling approach that is semi-automatic, and possibly fully-automatic, by combining polygon surface fitting (polyfit) technique and monoscopic multi-image measurement system. With the advent of dense matching and Structure from Motion methods (SfM), point clouds can be generated from multiple images obtained from digital cameras. Then, to reduce the data and to allow for efficient processing, it is necessary to extract polygonal surface data from point clouds delivered by the dense matching process. The polygonal surface is then used for the basis of further manual monoscopic measurements which are achieved separately on each image to obtain more detailed 3D model. Next, this approach analyzed the polygonal surface deformations in comparison to the initial point cloud data. It can be seen how the resolution and noise of the original point clouds affect the subsequent Polyfit-based modeling and monoscopic measurements. The deformations and the accuracy evaluation have been undertaken using different open source software. Also, the geometric error in the polyfit-derived polyhedral reconstruction propagating to the subsequent monoscopic-derived measurements was evaluated. Finally, our modeling approach shows that it can improve the processing speed and level of detail of the 3D models achieved using existing monoscopic measurements. Typically geometric accuracy itself doesn’t have enough information to make accurate geometry model.

show abstract

“…Consequently, the k-neighbourhood (also, known as k-nearest neighbours or k-NN) and r-neighbourhood [26] are two traditional approaches in selecting neighbours of a given point P i . The former selects k number of nearest points from P i , and the latter contains all points for which the distance to P i is less than or equal to r. Selecting the value for k or r is challenging as the local geometry of the object is unknown [17].…”

Section: Introductionmentioning

confidence: 99%

Effective Selection of Variable Point Neighbourhood for Feature Point Extraction from Aerial Building Point Cloud Data

et al. 2021

View full text Add to dashboard Cite

Existing approaches that extract buildings from point cloud data do not select the appropriate neighbourhood for estimation of normals on individual points. However, the success of these approaches depends on correct estimation of the normal vector. In most cases, a fixed neighbourhood is selected without considering the geometric structure of the object and the distribution of the input point cloud. Thus, considering the object structure and the heterogeneous distribution of the point cloud, this paper proposes a new effective approach for selecting a minimal neighbourhood, which can vary for each input point. For each point, a minimal number of neighbouring points are iteratively selected. At each iteration, based on the calculated standard deviation from a fitted 3D line to the selected points, a decision is made adaptively about the neighbourhood. The selected minimal neighbouring points make the calculation of the normal vector accurate. The direction of the normal vector is then used to calculate the inside fold feature points. In addition, the Euclidean distance from a point to the calculated mean of its neighbouring points is used to make a decision about the boundary point. In the context of the accuracy evaluation, the experimental results confirm the competitive performance of the proposed approach of neighbourhood selection over the state-of-the-art methods. Based on our generated ground truth data, the proposed fold and boundary point extraction techniques show more than 90% F1-scores.

show abstract

Robust Normal Estimation for 3D LiDAR Point Clouds in Urban Environments

Cited by 22 publications

References 39 publications

Advanced Methods for Point Cloud Processing and Simplification

Advanced Methods for Point Cloud Processing and Simplification

Polyfit Assisted Monoscopic Multi-Image Measurement Systems

Effective Selection of Variable Point Neighbourhood for Feature Point Extraction from Aerial Building Point Cloud Data

Contact Info

Product

Resources

About