Unlock instant, AI-driven research and patent intelligence for your innovation.

Point cloud downsampling method and device suitable for various scenes

A down-sampling and point cloud technology, applied in the field of computer vision, can solve the problems of being unable to adapt to the simplification requirements of 3D point cloud data, unable to fully retain 3D point cloud data, etc., to improve flexibility and versatility, and meet sampling accuracy and efficiency Effect

Pending Publication Date: 2022-06-03
深圳市凌云视迅科技有限责任公司 +1
View PDF0 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] This application provides a point cloud down-sampling method and device suitable for various scenarios, to solve the problem in the prior art that directly adopting a point cloud down-sampling method based on a voxel grid cannot adapt to a higher-precision 3D point cloud Data reduction requirements, and the feature points of 3D point cloud data cannot be fully preserved

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Point cloud downsampling method and device suitable for various scenes
  • Point cloud downsampling method and device suitable for various scenes
  • Point cloud downsampling method and device suitable for various scenes

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0073] like figure 1 As shown, this embodiment 1 provides a point cloud downsampling method suitable for various scenarios, and the method includes:

[0074] S101, obtain a 3D original point cloud, where the 3D original point cloud includes at least one boundary point and at least one non-boundary point;

[0075] S102, according to the scene of the 3D original point cloud, use a corresponding algorithm to extract the boundary area, the characteristic area and the non-feature area of ​​the 3D original point cloud, the boundary area includes at least one of the boundary points, the characteristic area The region contains at least one feature point, and the non-feature region contains at least one non-feature point; wherein, the boundary region is extracted by a corresponding boundary point detection algorithm, and the feature region and the non-feature region are obtained by a corresponding feature point extraction algorithm , and the feature region and the non-feature region a...

Embodiment 2

[0215] Corresponding to the above-mentioned Embodiment 1 of a point cloud downsampling method suitable for various scenarios, the present application also provides Embodiment 2 of a point cloud downsampling device suitable for various scenarios. The point cloud downsampling device includes an acquisition unit, an extraction unit, a point cloud downsampling unit and an output unit that are connected to each other;

[0216] Wherein, the acquisition unit is configured as:

[0217]obtaining a 3D original point cloud, the 3D original point cloud including at least one boundary point and at least one non-boundary point;

[0218] The extraction unit is configured to:

[0219] According to the scene of the 3D original point cloud, a corresponding algorithm is used to extract the boundary area, the characteristic area and the non-characteristic area of ​​the 3D original point cloud, the boundary area includes at least one of the boundary points, and the characteristic area includes a...

Embodiment 3

[0226] The present application provides a terminal device, including a memory, a processor, and a computer program stored in the memory and running on the processor. When the processor executes the computer program, one of Embodiment 1 is implemented. Steps for a point cloud downsampling method applicable to a variety of scenarios.

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention provides a point cloud downsampling method and device suitable for various scenes. The method comprises the following steps: acquiring a 3D original point cloud; according to the 3D original point cloud scene, a corresponding algorithm is adopted to extract a boundary region, a feature region and a non-feature region; performing point cloud downsampling processing on the feature points of the feature region to obtain a feature result point cloud; performing point cloud downsampling processing on non-feature points of the non-feature region to obtain non-feature result point cloud; and combining the boundary region, the feature result point cloud and the non-feature result point cloud as a 3D simplified point cloud to be output. According to the method, the boundary region is extracted through multiple boundary point detection algorithms, fine features are reserved to a great extent, the feature region and the non-feature region are extracted through multiple feature point extraction algorithms, most of the feature regions are reserved, the cavity phenomenon caused by too sparse non-feature points is avoided, and the accuracy of feature extraction is improved. And point cloud simplification is carried out on the feature region and the non-feature region by adopting a plurality of point cloud downsampling methods, so that the sampling precision and efficiency in different scenes can be met.

Description

[0001] Technology neighborhood [0002] The present application relates to the field of computer vision technology, and in particular, to a point cloud downsampling method and device suitable for various scenarios. Background technique [0003] At present, 3D machine vision detection technology has been widely used in the field of industrial intelligent manufacturing. In actual inspection projects, 3D machine vision inspection technology usually uses high-resolution cameras to obtain 3D point cloud data. The acquired 3D point cloud data has shortcomings such as high density, redundant information, and huge overall quantity. If you directly store and process all the acquired 3D point cloud data, it will take up huge computer memory space and consume a lot of time. time, resulting in low processing efficiency of 3D point cloud data. Therefore, it is necessary to downsample the massive and high-density 3D point cloud data through the point cloud downsampling algorithm, so as to...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G06T7/13G06T19/20
CPCG06T7/13G06T19/20G06T2207/10028G06T2200/04G06T2207/20192Y02P90/30
Inventor 周浩源彭斌姚毅全煜鸣
Owner 深圳市凌云视迅科技有限责任公司