Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Point cloud data processing method and device based on rotation and terminal equipment

A technology of point cloud data and processing methods, applied in three-dimensional object recognition, instrument, character and pattern recognition, etc.

Active Publication Date: 2019-09-24
暗物智能科技(广州)有限公司
View PDF7 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] Therefore, the technical problem to be solved by the embodiments of the present invention is that in the prior art, in order to ensure the rotation invariance of the point cloud data during the 3D rotation process, by providing a large amount of rotation enhanced data, the machine model is used to perform continuous training in a fixed manner, Its training method is not flexible enough, and it is difficult to ensure that the rotation robustness is guaranteed

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 data processing method and device based on rotation and terminal equipment
  • Point cloud data processing method and device based on rotation and terminal equipment
  • Point cloud data processing method and device based on rotation and terminal equipment

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0054] An embodiment of the present invention provides a feature processing method based on rotating point cloud data, such as figure 1 shown, including the following steps:

[0055] Step S1: Obtain target point cloud data. The target point cloud data here can be an image, and the image can be composed of many point clouds.

[0056] Step S2: Use the rotation mapping module to extract rotation invariant features from the target point cloud data. The rotation mapping module here is the RRI module, and the RRI module has been proved mathematically, which can ensure that the image data remains invariant during the rotation process, and that the image data will not be lost under normal conditions. Specifically, such as figure 2 As shown, the RRI module can be represented by the following formula for each point:

[0057]

[0058] The RRI module can represent the relative positional relationship between two points, in figure 2 p in i and p i1 can be represented by a vecto...

Embodiment 2

[0081] An embodiment of the present invention provides a feature processing device based on rotating point cloud data, such as Figure 8 shown, including:

[0082] An acquisition unit 81, configured to acquire target point cloud data.

[0083] The extraction unit 82 is configured to extract rotation-invariant features from the target point cloud data by using the rotation mapping module.

[0084] The multi-dimensional processing unit 83 is configured to use multiple clustering modules to perform multi-dimensional feature processing on the rotation-invariant features, and the multiple clustering modules are sequentially connected according to the number of clusters from large to small.

[0085] The classification unit 84 is configured to use a classifier module to classify the rotation-invariant features processed by the multi-dimensional features to obtain a classification result of the rotation-invariant features.

[0086] According to the feature processing device based on t...

Embodiment 3

[0101] An embodiment of the present invention provides a storage medium on which computer instructions are stored, and the steps of the method in Embodiment 1 are implemented when the instructions are executed by a processor. The storage medium also stores target point cloud data, rotation-invariant features, and the like. Wherein, the storage medium may be a magnetic disk, an optical disk, a read-only memory (Read-Only Memory, ROM), a random access memory (Random Access Memory, RAM), a flash memory (Flash Memory), a hard disk (Hard Disk Drive, abbreviated : HDD) or a solid-state hard drive (Solid-State Drive, SSD), etc.; the storage medium may also include a combination of the above-mentioned types of memory.

[0102] Those skilled in the art can understand that all or part of the processes in the methods of the above-mentioned embodiments can be completed by instructing related hardware through computer programs, and the programs can be stored in a computer-readable storage ...

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 discloses a feature processing method and device for point cloud data based on rotation and terminal equipment. The feature processing method comprises the steps: obtaining target point cloud data; extracting a rotation invariant feature from the target point cloud data by using a rotation mapping module; carrying out multi-dimensional feature processing on the rotation invariant features by utilizing a plurality of clustering modules, wherein the clustering modules are sequentially connected according to a clustering number sequence from large to small; and classifying the rotation invariant features processed by the multi-dimensional features by using a classifier module to obtain a classification result of the rotation invariant features. According to the invention, the rotation invariant features extracted from the target point cloud data are processed by combining the rotation mapping module and the plurality of clustering modules; the robustness of target recognition based on the 3D point cloud data can be ensured; the classification recognition precision of the target point cloud data is enhanced; and meanwhile the number requirement for training data of the deep learning model and the calculation cost during training of the deep learning model are reduced.

Description

technical field [0001] The present invention relates to the technical field of three-dimensional transformation processing of point cloud data, in particular to a processing method, device and terminal equipment of point cloud data based on rotation. Background technique [0002] The rotation transformation of point cloud is relatively common in the field of 3D technology, and at the same time, it causes inevitable challenges in 3D recognition. Theoretically, any 3D rotation can be combined by multiple operations, and the number of such combinations is infinite. Therefore, the machine learning model extracts features from a large input space, and trains the extracted features to ensure the classification accuracy of the point cloud data brought about by the rotation transformation. [0003] At present, in order to ensure the rotation invariance of point cloud data in the process of 3D rotation in the existing technology, a large amount of rotation enhanced data is often pro...

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
IPC IPC(8): G06K9/00G06K9/46G06K9/62
CPCG06V20/64G06V10/462G06F18/231G06F18/22
Inventor 陈添水陈嘉奇李冠彬陈超林倞
Owner 暗物智能科技(广州)有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Eureka Blog
Learn More
PatSnap group products