Image continuous matching method and system

Abstract

The invention relates to an image continuous matching method and system. The method comprises the following steps that: S1, a preset image size is calculated according to the size of a target image and the printing precision of a printing device, and an original image is processed according to the preset image size, so that an image to be matched can be obtained, wherein the original image is an image obtained through the shooting of the target image by a camera; S2: feature extraction is performed on the image to be matched, and all feature point information of the image to be matching is obtained, and feature matching is performed on the image to be matched and all reference images in a reference image library; S3, when matching fails, all sub-images of which the feature point number is smaller than a preset feature point number in the image to be matched are obtained; and S4, feature point adding processing is performed on the all the sub-images, so that a reference image is obtained, and the reference image is stored in an image matching reference image library. With the image continuous matching method and system of the invention, when detected feature points are not enough, feature points are added into the image to be matched, so that recognition degree can be improved, and therefore, the continuous matching and tracking of the target image can be realized.

Description

technical field [0001] The invention relates to the technical field of image matching, in particular to an image continuous matching method and system. Background technique [0002] Augmented reality provides users with a rich experience by superimposing virtual information into real-world scenes. In order to achieve good results, these computer-generated virtual objects need to be accurately aligned with real objects. Due to the uneven distribution of feature points in the image or the inability to detect the corresponding feature points when the camera is too far or too close to the target, it is easy to cause the matching failure of the target image, which further leads to the interruption of the target tracking. Contents of the invention [0003] The technical problem to be solved by the present invention is: in the prior art, due to the uneven distribution of feature points in the image or the inability to detect the corresponding feature points when the camera is too...

AI Technical Summary

Problems solved by technology

[0003] The technical problem to be solved by the present invention is: in the prior art, due to the uneven distribution of feature points in the image or the inability to detect the corresponding feature points when the camera is too far or too close to the target, the tracking of the target is easily interrupted

Images