A registration method of natural markers based on perspective classification

Abstract

The invention discloses a natural maker registration method based on viewpoint, and mainly overcomes shortcomings of poor real-time performance, large application restriction, and small effective viewpoint scope of a camera in conventional methods. The method has the realization steps of 1) acquiring an original image of a marker and a reference image, performing space division of a viewpoint of the camera, and generating viewpoint classification training samples by using image basic geometric transformations; 2) detecting viewpoint classification characteristics and binary system coding characteristics, and computing characteristic index values based on binary tests; 3) performing characteristic extraction on scene images based on marker target tracking, and performing characteristic retrieval and characteristic matching according to an adjacent viewpoint priority strategy; and 4) computing a homography array from the original image to the scene images and a camera external parameter array, and obtaining an accurate position of the marker in the scene according to the external parameter array, thereby completing marker registration. The natural marker registration method is strong in real-time performance, occupies little memory, and can be applied to an enhancement reality system based on markers with the advantage of wide effective viewpoint scope of the camera.

Description

technical field [0001] The invention belongs to the technical field of image processing, relates to computer vision and machine learning, in particular to a method for registering natural markers, which can be used for feature matching, recognition and tracking of target images. technical background [0002] The registration of markers is to extract the features of the images collected by the camera through the computer vision system, and perform feature matching with specific markers, so as to obtain the position information of the markers in the image scene, and track the markers in real time. One of the technical difficulties of marker registration is how to quickly identify markers in the scene, update the external parameter matrix of the camera in real time, and achieve the effect of fast and stable tracking of markers. According to different implementation methods, marker registration methods can be divided into two categories: 1) registration based on artificial marke...

AI Technical Summary

Problems solved by technology

At present, augmented reality based on such artificial markers is relatively mature, but this method has the following disadvantages: 1) Sensitive to local occlusion: for the grid pattern, occlusion will cause some grid points to be invisible, so that the recognition registration Ineffective, so checkered markers must work in an unobstructed environment

Although the concentric ring pattern has some anti-occlusion capabilities, it still cannot cope with the situation where the occlusion area is large.

2) The number of feature points used for matching is small, so the visual stability is poor

3) Placing artificial markers in the scene is not natural and beautiful, and there are many applications where artificial markers cannot be placed

It is more general than artificial markers, so it has wider applicability, but at the same time requires more complex recognition algorithm support

Compared with artificial marker registration, the main difficulties faced in the natural marker registration technology are reflected in the slow registration speed, poor real-time performance and large memory space occupation.

Images