Robust visual odometry method

By acquiring image feature points using a monocular camera, constructing epipolar geometric constraints, and filtering static feature points, the error problem caused by dynamic target interference in visual odometry on urban roads is solved, achieving higher accuracy and robust positioning, and is suitable for multi-scenario applications.

CN115830116BActive Publication Date: 2026-06-26BEIJING EYESTAR TECH CO LTD
View PDF 3 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
BEIJING EYESTAR TECH CO LTD
Filing Date
2022-12-05
Publication Date
2026-06-26

AI Technical Summary

Technical Problem

In complex environments such as urban roads, visual odometry systems suffer from large errors in feature point extraction and optical flow calculation due to interference from dynamic targets. In severe cases, the system diverges and cannot function properly.

Method used

A monocular camera is used to acquire two adjacent frames of images, extract feature points and match them, construct epipolar geometric constraint equations, calculate the initial rotation matrix and translation vector through singular value decomposition, convert them into three-dimensional world coordinates, filter static feature points, and re-estimate the actual essential matrix to obtain the camera pose change.

Benefits of technology

It improves the accuracy and robustness of visual odometry in complex environments, reduces the impact of dynamic objects on positioning, is suitable for indoor and outdoor scenarios, reduces costs, and does not rely on additional sensors.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN115830116B_ABST
    Figure CN115830116B_ABST
Patent Text Reader

Abstract

The application relates to a robust visual odometer method, which comprises the following steps: acquiring input images of two adjacent frames based on a monocular camera, and extracting feature points in the two input images respectively; acquiring a plurality of pairs of feature points, wherein the feature points are expressed in pixel plane coordinates; constructing an epipolar geometry constraint equation based on the pairs of feature points, and solving to obtain an initial essential matrix; using the initial essential matrix, and calculating an initial rotation matrix and an initial translation vector of the monocular camera between the two adjacent input images through singular value decomposition; converting the pixel plane coordinates of the pairs of feature points into three-dimensional world coordinates based on the initial rotation matrix and the initial translation vector; calculating the difference between the feature points in the pairs of feature points based on the three-dimensional world coordinates; judging whether the feature points are static feature points based on the difference, and if yes, the feature points are reserved; re-estimating the actual essential matrix of the monocular camera based on the static feature points, and obtaining an actual rotation matrix and an actual translation vector.
Need to check novelty before this filing date? Find Prior Art