A Filtering Algorithm for Scattered Point Cloud Based on Curvature Features Classification

Gu, Xiaoying

doi:10.12733/jics20105244

Cited by 6 publications

(4 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Furthermore, the parameter settings of these methods are valid for entire point cloud, and it is difficult to adjust parameters adaptively for different areas. Thus, some researchers proposed feature-based methods [7,[22][23][24][25] to recognize and classify feature areas and non-feature areas. On this basis, different filtering methods are used to remove noise for different areas.…”

Section: 3mentioning

confidence: 99%

Structural Feature-Preserving Point Cloud Denoising Method for Aero-Engine Profile

Yan

Zhou

Wang

et al. 2022

International Journal of Aerospace Engineering

View full text Add to dashboard Cite

The ex-service and old type aero-engines are valuable for education. In many cases, these aero-engines only have physical objects, but lack geometric models. This brings difficulties to talent cultivation. Therefore, the education department needs to reconstruct geometric models of above aero-engines. The laser scanning devices provide raw data of aero-engine profile, but noise directly affects reconstruction accuracy. In order to ensure that noise is removed without blurring or distorting structural features, a structural feature-preserving point cloud denoising method is proposed. The noisy point cloud is divided into casing feature data, pipeline feature data and complex shape feature data. According to shape characteristics of each feature data, three denoising networks are designed to estimate position correction vectors of noisy points and project them back onto underlying surfaces. Qualitative and quantitative experiments show that our method significantly outperforms state-of-the-art methods, both in terms of preservation and restoration of structural features.

show abstract

Section: 3mentioning

confidence: 99%

Structural Feature-Preserving Point Cloud Denoising Method for Aero-Engine Profile

Yan

Zhou

Wang

et al. 2022

International Journal of Aerospace Engineering

View full text Add to dashboard Cite

show abstract

“…This feature is an important one to obtain full information about the 3D point could obtained from range of sensors [9]. Given a depth image, the surface normal in this work is estimated similarly to the work of [10] by using the covariance analysis method based on local point cloud (Covariance Analysis, CA), also it is known as principal component analysis method. First by finding the nearest k-neighbour points of that point based on given a radius, then calculating the Covariance array of neighbours.…”

Section: The Datasetmentioning

confidence: 99%

“…The resulted histograms gave a stark and recognized difference in the histogram representations of handles and mug-body. See figures(9) and(10): The Histogram of the normal for the handles and the body of the mug.…”

mentioning

confidence: 99%

Detect the Correct Grasp in Mugs Using 3D Local Features

2019

JAUS

View full text Add to dashboard Cite

In this paper, the problem of grasping novel objects is considered. A new approach is suggested to predict the best grasp position from RGB-D images of mugs, specifically ones that are being seen for the first time through vision. In this work, by using surface normal and curvature as the local features of the 3D point cloud, we are able to use different machine learning models which can learn from these features to predict the graspable or the non-graspable position in a mug. Experimental evaluations show that these models are able to distinguish between the graspable part of a mug represented by the handle and other parts which considered as not-graspable. Keywords: Robots, Detection, Features, Machine-Learning, 3D-Model RESUMEN/ En este artículo, se considera el problema de captar objetos nuevos. Se sugiere un nuevo enfoque para predecir la mejor posición de agarre a partir de imágenes RGB-D de tazas, específicamente las que se ven por primera vez a través de la visión. En este trabajo, al usar la normalidad de la superficie y la curvatura como las características locales de la nube de puntos 3D, podemos usar diferentes modelos de aprendizaje automático que pueden aprender de estas características para predecir la posición comprensible o no en una taza. Las evaluaciones experimentales muestran que estos modelos pueden distinguir entre la parte agarrable de una taza representada por el asa y otras partes que se consideran no agarrables.

show abstract

“…However, the accuracy is reduced in the noise processing of sparse point clouds. Based on the different curvature characteristics of a point cloud model, Gu et al [20] proposed algorithms that used different filtering strategies for different curvature feature regions. Wu et al [21] applied the conventional median filtering and bilateral filtering algorithms to different feature regions and applied the filtering algorithm based on the average curvature feature classification, thus effectively removing noise and maintaining the geometric features of the sharp regions.…”

Section: Introductionmentioning

confidence: 99%

Overall Filtering Algorithm for Multiscale Noise Removal From Point Cloud Data

Ren

et al. 2021

IEEE Access

View full text Add to dashboard Cite

The multiscale noise in the 3D point cloud data of rock surfaces which collected by 3D scanners has a significant influence on the exploration of rock surface morphology. To this end, this paper proposes a multiscale noise removal overall filtering algorithm. The specific processing procedure of the algorithm is as follows. First, a weighted principal component analysis is performed on point cloud data, i.e., the neighboring point distance is used as a weight in the principal component analysis, the covariance feature matrix of the weighted point is estimated, and the eigenvector corresponding to the lowest eigenvalue is used as the normal vector of the point cloud data. Second, in the weighted principal component analysis, estimating three eigenvalues corresponding to the Eigen matrix of the point cloud data, the ratio of the eigenvalue corresponding to the normal vector to the sum of three eigenvalues is used as the surface change factor. For the sample point, if the surface change factor of one sample point is less than the average value of the surface change factor of all sample points in the neighborhood, the sample point belongs to a flat area; otherwise, it belongs to a mutation area. Finally, in order to achieve multiscale noise removal, statistical filtering algorithm is used to remove large scale noise in flat area, additionally bilateral filtering algorithm is adopted to remove small scale noise in mutation area. In the experiments, the improved principal component analysis is combined with the overall filtering algorithm to accurately estimate the eigenvalues of the point cloud data points. After that, the eigenvalues of the sample points are used to distinguish between flat area and mutation area, so as to consider large scale noise and small scale noise. From the experimental results, it can be seen that overall filtering algorithm can consider both large scale and small scale noise and can remove noise from the point cloud data of rock samples. Visual judgment, normal distribution and fractal distribution tests are employed on filtered rock sample point cloud data to verify the reliability of the filtering results.INDEX TERMS 3D scanner, point cloud data, multiscale noise, statistical filtering, bilateral filtering.

show abstract

A Filtering Algorithm for Scattered Point Cloud Based on Curvature Features Classification

Cited by 6 publications

References 7 publications

Structural Feature-Preserving Point Cloud Denoising Method for Aero-Engine Profile

Structural Feature-Preserving Point Cloud Denoising Method for Aero-Engine Profile

Detect the Correct Grasp in Mugs Using 3D Local Features

Overall Filtering Algorithm for Multiscale Noise Removal From Point Cloud Data

Contact Info

Product

Resources

About