View registration method, system and equipment based on dual quaternion and storage medium

A dual quaternion and registration technology, applied to systems, devices and storage media, in the field of view registration methods based on dual quaternions, can solve problems such as registration failure and low registration accuracy, and achieve reduced registration Error, the effect of improving the registration accuracy

Active Publication Date: 2019-07-02
BEIJING JINGDONG SHANGKE INFORMATION TECH CO LTD +1
View PDF10 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The technical problem to be solved by the present invention is to overcome the situation in the prior art that the ICP algorithm is used for 3D environment reconstruction based on the dense poi

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
  • View registration method, system and equipment based on dual quaternion and storage medium
  • View registration method, system and equipment based on dual quaternion and storage medium
  • View registration method, system and equipment based on dual quaternion and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0074] like figure 1 As shown, the dual quaternion-based multi-view registration method of this embodiment includes:

[0075] S101. Acquire multi-frame point cloud data, and select the first frame point cloud in the multi-frame point cloud data as a world coordinate system;

[0076] S102. Use the ICP algorithm to perform registration processing on any two adjacent frames of point cloud data in the multi-frame point cloud data, and obtain the multi-frame point cloud data after registration processing and the registration processing result; wherein, the registration processing The result is the first registration processing result;

[0077] Step S102 specifically includes:

[0078] S1021. Taking the point cloud of the first frame as a starting point, collect any two adjacent frames of point cloud data as source point cloud and target point cloud respectively;

[0079] Among them, when selecting the source point cloud and the target point cloud in the iterative process of the ...

Embodiment 2

[0140] like image 3 As shown, the difference between this embodiment and the dual quaternion-based multi-view registration method in Embodiment 1 is that step 1042 is different, specifically:

[0141] Step 1043, the relative coordinate transformation between the two adjacent frames of point cloud data and the rigid transformation between the point cloud data of each frame and several adjacent frames of point cloud data are processed by dual quaternion linear hybrid method, Obtain the rigid transformation of each frame point cloud to the world coordinate system;

[0142] Wherein, the several adjacent frames of point cloud data are used to represent several frames of point cloud data adjacent to the left and right of each frame of point cloud data.

[0143] Specifically, such as figure 2 As shown, when the dual quaternion linear hybrid method is used in step 104 to process each frame of point cloud data in the multi-frame point cloud data in step S102 and two adjacent frames...

Embodiment 3

[0164] like Figure 4 As shown, the multi-view registration system based on dual quaternions in this embodiment includes a first point cloud data acquisition module 1, a first registration processing module 2, a first judgment module 3, a selection unit 4, and a rigid transformation acquisition module 5. A second point cloud data acquisition module 6 , a second registration processing module 7 , a second judging module 8 and an output module 9 .

[0165] The first point cloud data acquisition module 1 is used to acquire multi-frame point cloud data;

[0166] The selection unit 4 is used to select the first frame point cloud in the multi-frame point cloud data as the world coordinate system;

[0167] The first registration processing module 2 uses the ICP algorithm to perform registration processing on any two adjacent frames of point cloud data in the multi-frame point cloud data, and obtains multi-frame point cloud data and registration processing results after registration ...

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 view registration method, system and equipment based on dual quaternion and a storage medium, and the method comprises the steps of obtaining the multi-frame point cloud data, and selecting a first frame point cloud in the multi-frame point cloud data as a world coordinate system; performing any two adjacent frames of registration by adopting an ICP algorithm to obtain each frame of point cloud data and a registration processing result; obtaining the rigid transformation by adopting a dual quaternion mixing method; obtaining new multi-frame point cloud data; adoptingan ICP algorithm to obtain new multi-frame point cloud data and a registration processing result; and judging whether the registration processing result converges or not until the registration processing result converges. According to the method, the problem of registration failure caused by the fact that data cannot be converged in the registration process only by adopting an ICP algorithm in theprior art is solved; and through fusion of a dual quaternion mixing method and an ICP algorithm, the registration errors generated in a multi-view pairwise registration process are reduced, so that the registration precision is improved.

Description

technical field [0001] The invention relates to the technical field of three-dimensional data reconstruction, in particular to a dual quaternion-based view registration method, system, device and storage medium. Background technique [0002] The essence of the 3D environment reconstruction process is to fuse and align environmental information from different perspectives to restore the entire real 3D scene. The reconstruction technology of 3D environment is widely used in many new fields such as robot autonomous navigation, unmanned driving and unmanned aerial vehicles. [0003] According to the different types of sensors used, the key technologies used in the reconstruction process of the 3D environment are also very different. In the prior art, the following two reconstruction techniques are commonly used: [0004] (1) Feature-based environmental modeling: Feature-based map construction uses monocular or binocular to reconstruct the three-dimensional environment. This me...

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): G06T7/33
CPCG06T7/33G06T2207/10016G06T2207/10028
Inventor 陈桂芳
Owner BEIJING JINGDONG SHANGKE INFORMATION TECH CO LTD
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
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap