Robot vision positioning method based on feature point detection and mismatching screening

Abstract

The invention provides a robot vision positioning method based on feature point detection and mismatching screening. The robot vision positioning method comprises the following steps: A, constructinga Gaussian image pyramid; B, performing FAST feature point detection on each layer of image by using a quadrilateral model; C, constructing a BRIEF descriptor for the extracted feature points based onneighborhood pixel values; D, conducting violence matching based on the BRIEF descriptor; and E, screening mismatched feature points, and corresponding the matched feature points to an original reference image and a to-be-matched image based on a screening result. The method has the advantages that the feature points are detected in a quadrilateral mode, the detection speed is improved, the defect that the FAST feature points do not have scales is eliminated by constructing a Gaussian image pyramid, and based on violent matching, the feature points can be matched with each other, then the mismatched feature points are screened, and a correct matching result is reserved, so that pose calculation is facilitated.

Description

technical field [0001] The invention relates to the technical field of image detection, in particular to a robot vision positioning method based on feature point detection and mismatch screening. Background technique [0002] In the field of image detection of computer vision, image feature extraction and matching are important links in robot vision positioning. Robot vision positioning is often used in simultaneous positioning and mapping (Simultaneous Localization and Mapping, SLAM), which refers to the mobile carrier equipped with specific sensors, such as Depth cameras, lidars, and inertial measurement units. In an unknown environment, the carrier starts from a certain point. During the movement, the image and depth information collected by the sensor are repeatedly used to estimate its own trajectory and build incrementally. Map information of the surrounding environment. The SLAM system includes visual odometry, back-end optimization, loop detection, building Figure ...

AI Technical Summary

Problems solved by technology

However, the image feature extraction of this scheme uses SURF feature points with a large amount of calculation, which affects the calculation speed of the algorithm, and the RANSAC algorithm treats all matching point pairs equally, and uniformly draws random samples from the entire set; the data of the RANSAC algorithm building model has random sex, uncertainty

Images