Automatic high-precision registration method of point cloud and image based on mutual information

A technology of mutual information and high precision, applied in the field of photogrammetry and lidar, can solve problems such as poor robustness, unsatisfactory texture resolution and positioning accuracy, and unsuitable for irregular complex objects, and achieve accurate registration. , the effect of eliminating projection differences

Active Publication Date: 2021-10-15
BEIJING UNIV OF CIVIL ENG & ARCHITECTURE
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The automatic registration of the two data has always been the focus of research by scholars at home and abroad. At present, the main methods for the automatic registration of ground laser and point cloud are: the integration of sensors, and many instrument companies have launched scanners with built-in cameras, which can directly scan out color points. cloud, but the texture resolution and positioning accuracy do not meet the requirements; for feature-based registration, most studies focus on extracting the homonym line features of point cloud and image for registration, this method is not suitable for irregular complex objects, and the homonym Automatic extraction of feature points Due to the non-homogeneous heterogeneity of the two types of data, it is difficult to obtain the correct point pairs with the same name based on the matching of image grayscale information, and the robustness is poor

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
  • Automatic high-precision registration method of point cloud and image based on mutual information
  • Automatic high-precision registration method of point cloud and image based on mutual information
  • Automatic high-precision registration method of point cloud and image based on mutual information

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0087] The present invention will be further described below in conjunction with the accompanying drawings to make those skilled in the art with reference to the specification.

[0088] It will be appreciated that, such as "having", "including" and "including" as used herein do not match the presence or addition of one or more other elements or combinations thereof.

[0089] Based on the registration of mutual information, research applies to registration of aerial image and airborne radar with POS data, but the feasibility of the algorithm is affected by factors such as data volume and texture.

[0090] like figure 1 As shown, the present invention provides a point cloud and video automatic high precision registration method based on mutual information, including:

[0091] Step 1, take the close-up optical image of the object to be tested;

[0092] Step Second, the ground laser scanning point cloud to be tested, then utilize the visible light spectrum information and laser reflec...

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 automatic high-precision registration method for point clouds and images based on mutual information, comprising: shooting close-range optical images of objects to be measured; collecting ground laser scanning point clouds of objects to be measured, and generating RGB color images and reflection intensity images; Use close-range optical images and point cloud RGB color images to calculate rough registration parameters; divide the reflection intensity image into grids to extract Harris operator feature points, and apply Forstner positioning operators for precise positioning, and use coarse registration parameters to calculate feature points. Corresponding to the initial position of the point with the same name, use the mutual information theory to search for the exact matching point of the feature point in the close-range optical image within the initial position, and obtain the exact feature point pair of the same name in the two images; then calculate the fine registration parameters; generate Accurate color point cloud model of the object to be measured. The invention is not affected by non-homologous data projection and radiation difference, and meets the demand for high-precision three-dimensional color texture model reconstruction in the cultural relics protection industry.

Description

Technical field [0001] The present invention relates to photographic measurement and laser radar technology, and in particular, the method of automatic high precision registration based on mutually information-based point cloud and video. Background technique [0002] With the development of China's science and technology and economy, the emphasis on cultural relics is continuously improved, and the level of cultural relics protection, management and utilization has higher requirements, including cultural relic three-dimensional data display, cultural relics, cultural relics simulation model, Cultural relics derivative goods and the like. Cultural relics High-precision 3D color model reconstruction is the basis of cultural relics digital protection, usually the application of ground laser scanning point clouds and close-up image registration and texture mapping, and the registration of the two data is the key content of high precision 3D reconstruction. The automatic registration...

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 Patents(China)
IPC IPC(8): G06T7/33G06T17/00
CPCG06T17/00G06T2207/10024G06T2207/10028G06T7/33
Inventor 胡春梅夏国芳薛惠敏
Owner BEIJING UNIV OF CIVIL ENG & ARCHITECTURE
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