Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

A weight-optimized point-line integrated visual-inertial odometry method

An odometer and weight technology, applied in the field of computer vision, can solve problems such as algorithm robustness and stability effects, solution results and accuracy effects, system failures, etc.

Active Publication Date: 2021-09-14
BEIHANG UNIV
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, in the visual part of the inertial visual odometer, due to environmental factors such as poor lighting and environmental texture conditions, the system fails to collect enough feature points, which has a great impact on the robustness and stability of the algorithm. big impact
In addition, the mismatch in feature matching will also have a negative impact on the solution results and accuracy of the system

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 weight-optimized point-line integrated visual-inertial odometry method
  • A weight-optimized point-line integrated visual-inertial odometry method
  • A weight-optimized point-line integrated visual-inertial odometry method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0035] Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited by the embodiments set forth herein. Rather, these embodiments are provided for more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art.

[0036] The embodiment of the present invention discloses a weight-optimized point-line comprehensive visual-inertial odometer method, such as figure 1 shown, including the following specific steps:

[0037] S1. Use the camera and IMU mounted on the carrier to collect environmental information and motion information, select key frames, perform sliding window edge processing on the key frames, and realize the extraction and managemen...

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 weight-optimized point-line comprehensive visual inertial odometer method, the steps of which are as follows: use a camera and an IMU carried by a carrier to collect environmental information and motion information, and realize the extraction and management of point features and line features, and the IMU Pre-integration of motion information; use point features, line features, and IMU residuals to obtain the initial pose calculation objective function; use nonlinear weights based on word frequency to suppress unstable features, and optimize the objective function model composed of various residuals ; Use the optimized objective function to calculate the position and motion of the carrier. The present invention provides a weight-optimized point-line comprehensive visual inertial odometry method, using characteristic straight lines to solve the problem of fewer features in weak texture scenes, and using nonlinear weights to optimize the feature residual model to achieve weak textures Stable and effective operation of visual-inertial odometry in the scene.

Description

technical field [0001] The invention relates to the technical field of computer vision, and more specifically relates to a weight-optimized point-line comprehensive visual-inertial odometer method. Background technique [0002] Visual-inertial odometry is one of the common integrated navigation methods, which has the characteristics of low cost, small size and convenience. In recent years, with the development of small platforms, visual inertial odometry has been widely used, and the requirements for algorithm accuracy, applicable environment and stability are also increasing. However, in the visual part of the inertial visual odometer, due to environmental factors such as poor lighting and environmental texture conditions, the system fails to collect enough feature points, which has a great impact on the robustness and stability of the algorithm. big impact. In addition, the mismatching that occurs during feature matching will also have a negative impact on the solution r...

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): G01C21/16G01C3/00G01C22/00
CPCG01C3/00G01C21/16G01C22/00
Inventor 赵龙赵毅琳
Owner BEIHANG UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com