A rgb-d image registration method based on 2d/3d mode switching

An RGB image, RGB-D technology, applied in the field of RGB-D image registration based on 2D/3D mode switching, can solve the problem of low image registration quality, reduce calculation time, widen application time and space, The effect of improving robustness

Active Publication Date: 2020-05-26
CHINA UNIV OF MINING & TECH
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0008] Aiming at the problem of low image registration quality in the prior art, the purpose of the present invention is to provide a RGB-D image registration method based on 2D / 3D mode switching, and the RGB-D image of the environment can be acquired simultaneously by using the RGB-D sensor. and Depth image information, determine the priority of the registration mode according to the image quality inspection results, and use the remaining image registration method to supplement it to achieve accurate image registration

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
  • A rgb-d image registration method based on 2d/3d mode switching
  • A rgb-d image registration method based on 2d/3d mode switching
  • A rgb-d image registration method based on 2d/3d mode switching

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0025] The present invention will be further explained below in conjunction with the accompanying drawings and specific embodiments.

[0026] Step 1. Use the RGB-D sensor to collect environmental information, and output a sequence of RGB images and Depth images;

[0027] Step 2. Randomly extract N sample images from the collected environmental information, respectively detect their RGB image quality α and Depth image quality β, and determine the priority of the registration modality according to the detection results;

[0028] Step 3. Among the N samples, if the ratio of good-quality images in the RGB image to the entire sample is greater than the ratio of good-quality images in the Depth image to the entire sample, the 2D registration method has a high priority; otherwise, the 3D registration method The quasi-method has high priority. If the texture information and structure information in the environment are equally rich, that is to say, the quality of the RGB image and the...

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 RGB-D image registration method based on 2D/3D mode switching, and the method comprises the steps: obtaining an RGB image and a Depth image of an environment through an RGB-D sensor; respectively carrying out the detection of the quality of the RGB image and the quality of the Depth image through an image quality detection method; determining the priority of a registration mode according to the image quality, and carrying out the supplementation for the priority through employing the other remaining image registration algorithm; abandoning an image with the poor quality, thereby reducing the image registration time. The method makes the reasonable use of the information of 2D/3D modes, greatly improves the robustness and instantaneity of image registration, increases the application time and space of a mobile robot, and is enabled to be adapted to a more complex environment.

Description

technical field [0001] The invention belongs to the field of autonomous navigation and positioning of mobile robots, in particular to an RGB-D image registration method based on 2D / 3D mode switching. Background technique [0002] The robot's cognition of the surrounding environment and its self-localization are the prerequisites for its autonomous navigation. Therefore, the problem of Simultaneous Localization and Mapping (SLAM) plays a pivotal role in the research field of autonomous mobile robots. In the past ten years, SLAM based on visual sensors has achieved a lot of research results. In a relatively simple structured environment, the robot can build a map of the environment and achieve self-localization, complete navigation and other tasks. However, in a complex unstructured environment, the environmental color and brightness of the image are easily affected by changes in lighting, weather, and seasons. Robots still face many difficulties and challenges in order to ac...

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): G06T7/30G06T7/90
Inventor 缪燕子金鑫卜淑萍许红盛金慧杰李晓东周笛
Owner CHINA UNIV OF MINING & TECH
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