Unlock instant, AI-driven research and patent intelligence for your innovation.

A Method for Restoring Relative Pose of Stereo Image Pairs

A stereoscopic image and relative attitude technology, applied in the field of computer vision, can solve problems such as difficulty in ensuring uniform distribution of sample points, influence on calculation accuracy, and large amount of calculation, and achieve rapid restoration of relative attitude of stereoscopic images, optimize design and manufacture, and improve real-time sexual effect

Active Publication Date: 2022-07-05
WUHAN UNIV
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Therefore, when the number of corresponding points is large, the traditional method usually requires a large number of iterations, which leads to a large amount of calculation and a long time-consuming problem.
Moreover, the sample points are randomly distributed during random sampling, and it is difficult to ensure that the sample points are evenly distributed on the image, which will affect the calculation accuracy

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 Method for Restoring Relative Pose of Stereo Image Pairs
  • A Method for Restoring Relative Pose of Stereo Image Pairs
  • A Method for Restoring Relative Pose of Stereo Image Pairs

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0036] The technical solutions of the present invention will be further described below with reference to the accompanying drawings and embodiments.

[0037] The present invention provides a method for restoring the relative posture of a stereoscopic image pair. First, use all the corresponding points in the image pair to construct the equation, and directly calculate the essential matrix according to the properties of the essential matrix, then remove the gross errors in the corresponding points according to the obtained essential matrix, and solve the essential matrix and remove the gross errors. Repeat several times until new gross errors cannot be detected, and finally decompose the obtained essential matrix to obtain the relative pose of the stereo image pair.

[0038] like figure 1 As shown, the process of the embodiment of the present invention includes the following steps:

[0039] It is established that there are N pairs of corresponding points in the volume image, ...

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 belongs to the field of computer vision, and relates to a method for restoring the relative posture of a stereoscopic image pair. The invention uses all corresponding points in the stereo image pair to construct an equation system through epipolar constraints and solve the essential matrix; selects the optimal essential matrix; detects and removes gross errors, and judges whether to perform iteration according to the gross error detection results When a new gross error occurs, the iteration ends, and the currently selected essential matrix is ​​decomposed to restore the relative pose of the stereo image pair. The invention avoids the random sampling problem of RANSAC while ensuring the accuracy, improves the calculation speed, saves the system resources and improves the real-time performance.

Description

technical field [0001] The invention belongs to the field of computer vision, and in particular relates to a method for restoring the relative posture of a stereoscopic image pair. Background technique [0002] Stereo image pair relative pose recovery is a fundamental problem in photogrammetry and computer vision. In photogrammetry and computer vision, it is widely used in 3D scene reconstruction, motion matching, autonomous navigation control of intelligent robots, geometric positioning of photogrammetry, vehicle mobile measurement, low-altitude UAV measurement, etc. [0003] It is a common method in computer vision to recover the relative pose of a stereo image pair by solving and decomposing the essential matrix. The essential matrix is ​​determined by the rotation matrix and the translation vector, and can be directly calculated using the normalized coordinates of the corresponding points. The traditional method of directly solving the essential matrix is ​​usually com...

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): G06T7/593G06T7/80G01C11/00G06F17/16
Inventor 赵双明崔云帆常青
Owner WUHAN UNIV