Advanced sampling consistency image matching algorithm

Abstract

The invention relates to the technical field of image processing, in particular to an advanced sampling consistency image matching algorithm. The method comprises the following steps: reading two pictures to be matched, constructing an image pyramid for each picture, and completing initialization; detecting the position of an Oriented FAST corner point in the picture, and setting a threshold valueby using an iterative method; extracting a FAST key point; calculating a BRIEF descriptor according to the angular point position; carrying out 2-4 operations on each layer of picture of the image pyramid; performing grid processing on the image, performing feature matching through a violent matching method, and classifying the descriptors by using a bag-of-words model when prior information is lacked in the matching process; calculating quality factors of the matching points in a grouping manner, sorting in a descending order, screening the matching points, and removing mismatching points; and drawing matching results. The randomness of algorithm sampling is reduced, the success rate of obtaining a correct model is improved, the number of iterations of the system is greatly reduced, thespeed of the algorithm is improved, and the total calculation time of the system is reduced.

Description

technical field [0001] The invention relates to the technical field of image processing, in particular to an advanced sampling consistency image matching algorithm. Background technique [0002] The method of visual navigation has a long history, from simple monocular visual odometer to binocular visual odometer, and then to vision-based SLAM (Simultaneous Localization and Mapping), the research on visual navigation has made great progress. progress. In 1980, Moravec proposed the framework of visual odometry, and the visual odometry that has appeared since then is based on this framework, mainly including feature extraction, matching, tracking, and back-end pose estimation. [0003] In recent years, in computer vision processing, when the observation environment such as angle and distance changes, corner points may be misjudged as ordinary points, and ordinary points may also be misjudged as corner points. In order to solve this problem, the field of computer vision define...

AI Technical Summary

Problems solved by technology

[0005] However, in actual operation, due to the influence of lighting, translation, and smear caused by camera shake, the feature points may not always be matched, and there may even be false matching.

This will reduce the accuracy of the homography matrix between the left and right frames, which in turn affects the measurement accuracy of the computer vision system

Images