VIO rapid united initialization method based on monocular camera

An initialization method, camera technology, applied in navigation through speed/acceleration measurement, image data processing, instruments, etc.

Active Publication Date: 2018-12-11
SOUTHEAST UNIV
View PDF6 Cites 13 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Another initialization method introduced by VINS proposed by HKUST provides a robust initialization process capable of bootstrapping the system from an unknown initial state, but requires a lot of computing resources to calculate the gravity direction

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
  • VIO rapid united initialization method based on monocular camera
  • VIO rapid united initialization method based on monocular camera
  • VIO rapid united initialization method based on monocular camera

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0062] Such as figure 1 As shown, the VIO fast joint initialization method based on the monocular camera includes the following steps:

[0063] (1) Process a few seconds of video with ORB-SLAM to obtain the initial pose and a few keyframes;

[0064] (2) construct cost function calculation gyroscope deviation by the key frame in the step (1) and IMU pre-integration;

[0065] (3) Obtain the gravity accelerometer bias, gravity acceleration, gravity acceleration calibration and gravity accelerometer bias by solving the linear model between consecutive frames;

[0066] (4) Calculate the scale and velocity information through the gravitational acceleration calibration and parameter separation in step (3).

[0067] Step 1. Gravity accelerometer bias estimation

[0068] The motion between two consecutive keyframes can be described by the pre-integrated ΔR, Δv, Δp measured between the two frames. From the pre-integration equation:

[0069]

[0070]

[0071]

[0072] i and...

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 VIO rapid united initialization method based on a monocular camera. The VIO rapid united initialization method comprises the following steps: (1) processing a few seconds ofvideo by using ORB-SLAM to obtain an initial pose and several keyframes; (2) calculating a gyroscope deviation by using the keyframes in the step (1) and an IMU pre-integral construction cost function; (3) resolving gravity accelerometer bias, gravity acceleration, gravity acceleration calibration and gravity accelerometer bias by resolving a linear model among continuous frames; and (4) resolvingdimension and speed information by the gravity acceleration calibration in the step (3) and parameter separation. The initialization method disclosed by the invention is higher in initialization speed and has little influences to positioning accuracy. By using the method disclosed by the invention, the initialization time can be controlled within 10 s; and the speed increment of united initialization is of great significance to improve the real-time performance.

Description

technical field [0001] The invention relates to the technical field of robot vision positioning and navigation, in particular to a VIO fast joint initialization method based on a monocular camera. Background technique [0002] State estimation for smart mobile terminals has become a hot topic in computer vision and robotics because of its applications in emerging technologies such as micro air vehicles, autonomous vehicles, virtual reality and augmented reality. Traditional intelligent mobile terminal positioning is divided into outdoor positioning and indoor positioning. Outdoor positioning includes satellite positioning and base station positioning, while indoor positioning mainly relies on multi-sensor fusion. Among the different sensor systems, visual-inertial systems have attracted much attention due to their small size, low cost, and great potential. There are two main methods for estimating the pose of visual-inertial systems: nonlinear optimization methods and recu...

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 Applications(China)
IPC IPC(8): G01C21/16G01C21/20G06T7/73
CPCG01C21/16G01C21/20G06T7/75
Inventor 潘树国黄砺枭王帅曾攀
Owner SOUTHEAST 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