Point Cloud Reduction and Denoising Based on Optimized Downsampling and Bilateral Filtering

Zou, Bochang; Qiu, Huadong; Lu, Yutong

doi:10.1109/access.2020.3011989

Cited by 32 publications

(21 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In our method, first, in order to solve the damage of the point cloud surface structure caused by downsampling, the FWD method is adopted.The spatial structure of the point cloud is preserved by this method [6],the effect is better than existing methods.Secondly, in order to further improve the accuracy of the search method, a new search method KK octant search is proposed.On the basis of octant search, the threshold is set to further filter, so that the obtained points are more suitable for the same characteristics.The most important point is the problem of the correlation between adjacent coordinates and the input, and the problem of difficult segmentation of multiple connected regions.A combination of multiple features is proposed to fully extract spatial and geometric information,compared with the latest method SAN, better performance is achieved.…”

Section: Introductionmentioning

confidence: 93%

“…FWD uses a combination of farthest-point sampling and down-sampling. Compared with only farthest-point sampling, more suitable samples can be taken; the effect of FWD has been proved by [6]. In Fig.…”

Section: A Multi-scale Feature Framework(mff)mentioning

confidence: 99%

“…This method works as follows: 1. Farthest-point weighted mean down-sampling (FWD) [6] is used for sampling. 2.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

MLFNet- Point Cloud Semantic Segmentation Convolution Network Based on Multi-Scale Feature Fusion

et al. 2021

Self Cite

View full text Add to dashboard Cite

The project was funded by jinan science and technology bureau and undertaken by QiluUniversity of Technology(Shandong Academy of Sciences),Machine vision-based online intelligentsegmentation of foreign objects in liquids is implemented.2019GXRC067. ABSTRACTIn the semantic segmentation of a point cloud, if the spatial structure correlation between the input features and coordinates are not fully considered, a semantic segmentation error can occur. We propose a method of spatial convolution that makes full use of the characteristics of a multiscale spatial structure by combining local and global features. We call this method MLFNet. We also propose a multiscale feature framework. First, the point cloud is simplified by obtaining the weighted farthest point (by down-sampling combined with farthest-point sampling and the weighted average). The near-near domain of each sampling point is then obtained by a KK octant search (an octant search optimized by the knearest neighbor and a custom threshold), and feature information is obtained. The feature information is added to the subsequent multilayer perceptron, and fusion of local context information is achieved. Finally, the fusion features in multiple directions are maximally pooled. Our method was tested on self-made datasets and other standard basic datasets (ModelNet40, ShapeNet, and Stanford large-scale 3D indoor spaces (S3DIS) data). The accuracy of segmentation was 0.937 in our dataset; two percentage points higher than the latest deep learning method. Also, our method obtained a mean intersection over a union of 0.867 in ShapeNet, which was 0.3 percentage points higher than the latest PointGrid. The accuracy on S3DIS was 0.8153, which was three percentage points higher than the latest spatial aggregation net. The results of semantic segmentation verified the superiority of the proposed method.

show abstract

Section: Introductionmentioning

confidence: 93%

Section: A Multi-scale Feature Framework(mff)mentioning

confidence: 99%

See 1 more Smart Citation

MLFNet- Point Cloud Semantic Segmentation Convolution Network Based on Multi-Scale Feature Fusion

et al. 2021

Self Cite

View full text Add to dashboard Cite

show abstract

“…In the above article [1], when we edited the affiliations of authors, their old names were provided and the new names were not added. As a result, when other researchers queried the authors of [1], the affiliations of authors were not found due to the incorrect affiliations in the article [1]. These affiliations caused incomplete information.…”

mentioning

confidence: 99%

“…In this article, the affiliations of authors are corrected by us. After affiliations are revised, the affiliations do not affect the results and analysis of the article [1].…”

mentioning

confidence: 99%

Corrections to “Point Cloud Reduction and Denoising Based on Optimized Downsampling and Bilateral Filtering”

Zou

Qiu

2020

IEEE Access

Self Cite

View full text Add to dashboard Cite

Improvement of 3D reconstruction based on a new 3D point cloud filtering algorithm

Hazzat

Merras

2023

SIViP

View full text Add to dashboard Cite

Point Cloud Reduction and Denoising Based on Optimized Downsampling and Bilateral Filtering

Abstract: The project was funded by jinan science and technology bureau and undertaken by qilu university of technology, Machine vision-based online intelligent detection of foreign objects in liquids is implemented.2019GXRC067.

Cited by 32 publications

References 35 publications

MLFNet- Point Cloud Semantic Segmentation Convolution Network Based on Multi-Scale Feature Fusion

MLFNet- Point Cloud Semantic Segmentation Convolution Network Based on Multi-Scale Feature Fusion

Corrections to “Point Cloud Reduction and Denoising Based on Optimized Downsampling and Bilateral Filtering”

Improvement of 3D reconstruction based on a new 3D point cloud filtering algorithm

Contact Info

Product

Resources

About