Improved three-dimensional point cloud registration method and system based on two-dimensional image guidance, and readable storage medium

A technology of 3D point cloud and 2D image, which is applied in image enhancement, image analysis, image data processing, etc. It can solve the problems of low precision and low efficiency of ICP registration calculation, and achieve the effect of improving accuracy

Pending Publication Date: 2020-03-31
HUNAN UNIV +1
View PDF2 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] The present invention proposes an improved 3D point cloud registration method, system and readable storage medium based on 2D image gu

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
  • Improved three-dimensional point cloud registration method and system based on two-dimensional image guidance, and readable storage medium
  • Improved three-dimensional point cloud registration method and system based on two-dimensional image guidance, and readable storage medium
  • Improved three-dimensional point cloud registration method and system based on two-dimensional image guidance, and readable storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0078] Below in conjunction with accompanying drawing and embodiment the present invention will be further described

[0079] On the basis of the classic ICP algorithm, the present invention provides an improved ICP registration method based on RGB-D cameras to obtain depth images. The algorithm improves the calculation efficiency and accuracy, and can be widely used in 3D scene construction and robot 3D pose estimation. and other fields [1-2] .

[0080] Such as figure 1 As shown, an improved ICP registration method based on RGB-D camera to obtain depth images, including the following steps:

[0081] Step 1: Obtain the two-dimensional color image I of the adjacent frame scene t , I t+1 and the corresponding depth image D t 、D t+1 ;

[0082] Use the RGB-D camera to acquire the two-dimensional color image I of the adjacent frame scene at time t and t+1 t and I t+1and a depth image D corresponding to the two-dimensional color image t and D t+1 ;

[0083] Step 2: Depth...

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 an improved three-dimensional point cloud registration method and a system based on two-dimensional image guidance, and a readable storage medium. According to the method, a point-to-surface distance is used as the measurement of a target function; a nearest neighbor point is searched by using a FLANN nearest neighbor algorithm searching method; a depth image filtering method based on color image guidance and a PCA-based method are successively used to carry out downsampling. According to the method, the depth point accuracy is improved, meanwhile, the calculation amount of the subsequent iteration process is reduced, rapid three-dimensional point cloud registration can be achieved, the method has the advantages of being high in robustness, small in calculation amount and the like, and the urgent requirements for three-dimensional point cloud registration in the application fields of robot self-positioning, map creation and the like are effectively met.

Description

technical field [0001] The invention belongs to the field of robot vision control, in particular to an improved three-dimensional point cloud registration method, system and readable storage medium based on two-dimensional image guidance. Background technique [0002] Depth image registration is to calculate the rotation and translation matrices corresponding to different viewing angles according to the overlapping constraints of point clouds between scenes under different viewing angles, which is a key step in 3D scene construction and robot 3D pose estimation. With the increasing maturity of depth image information acquisition technologies such as 3D lidar, stereo camera, and 3D camera, depth image registration has shown great advantages in applications such as 3D scene modeling, scene recognition, and robot navigation and positioning. The accuracy and efficiency of depth image registration directly determine the performance of tasks such as 3D scene construction, 3D motio...

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): G06T7/33G06T5/50G06K9/62
CPCG06T7/33G06T5/50G06T2207/10028G06T2207/20221G06F18/2135
Inventor 余洪山付强王佳龙郭林峰王静文
Owner HUNAN UNIV
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