Visual positioning method and device

Abstract

The invention discloses a visual positioning method and device. The method comprises the following steps of firstly determining continuous frames of images collected by an image sensor according to the two frames of images and inertia data, determining pose change data of the image sensor; determining an essential matrix of the two frames of images; respectively determining each feature point in the two frames of images; matching feature points to obtain each feature point pair; for each feature point pair, determining the matching degree of two feature points in the feature point pair according to the determined essential matrix, finally determining the feature point pair of which the matching degree is within the preset threshold interval from the feature point pairs according to the preset threshold interval, and performing visual positioning according to the screened feature point pairs. The matching degree of each feature point pair is determined through the essential matrix, so that the feature points with higher matching degree are screened out and sent to the rear end, the rear end performs visual positioning according to the feature points with higher matching degree, thepositioning is more accurate, and the map construction precision is higher.

Description

technical field [0001] The present application relates to the field of computer technology, in particular to a visual positioning method and device. Background technique [0002] At present, the visual positioning system usually consists of a front-end and a back-end. The front-end is a terminal for collecting image data, extracting feature points and matching feature points, such as robots, vehicles, etc., and the back-end is based on the features matched by the front-end. A device, usually a server, that optimizes processing, positioning, and building maps. Among them, the accuracy of feature point matching determined by the front-end directly affects the accuracy of back-end positioning and map construction. The higher the accuracy of feature point matching, the higher the accuracy of the visual positioning system. [0003] Generally, in order to improve the accuracy of feature point matching in the prior art, the front end can also filter the feature point pairs obtaine...

AI Technical Summary

Problems solved by technology

[0005] However, when the proportion of outliers eliminated by RANSAC is large, it means that the feature point pairs determined by optical flow tracking are not accurate, so that the outliers cannot be accurately eliminated according to the basic matrix.

Or when the number of determined feature point pairs is small, the accuracy of the determined basic matrix will also be reduced, which will further cause the RANSAC algorithm to eliminate outliers inaccurately, affecting the accuracy of back-end positioning and map construction

Images