Mobile robot visual localization method based on improved Apriltag tags

Abstract

The invention puts forward a virtual studio mobile robot visual localization method based on improved Apriltag tags, comprising the following steps: adding four uniformly-sized ring markers at the appropriate length of quadrilateral diagonal extension cords of a tag; calibrating a camera; acquiring tag images: preprocessing the acquired images; carrying out threshold processing on ROI region extraction; identifying elliptical markers; extracting the ROI region; carrying out threshold processing on the minimum rectangular area surrounding the four points which is the ROI tag area of the tag images with the coordinates of four ellipse centers on the improved tags as the benchmark; extracting tag corner points and fitting the extracted straight lines by the weighted least square method, calculating intersection points of straight lines to obtain subpixel-level corner point coordinate, and extracting image coordinates of the tag corner points; reading the coded message of the tags according to the extracted image coordinates of the corner points, obtaining world coordinates of the corner points, and obtaining the pose of a robot by coordinate transformation. The method of the inventionhelps reduce the data size of the identification tags and improve the real-time performance of identification.

Description

technical field [0001] The invention belongs to the field of machine vision, in particular to a mobile robot vision positioning method based on an improved Apriltag tag. Background technique [0002] With the development of society and the advancement of science and technology, the application fields of robots are becoming more and more extensive, among which indoor mobile robots are the current focus of development and research. In order for the mobile robot to complete the corresponding movement according to the pre-set commands, the position information of the robot should be determined first in the current state. Therefore, the research of positioning technology is the core of mobile robot research. [0003] Compared to the outdoor environment, the indoor environment is characterized by low light, a small field of view, and a structured environment. The indoor mobile robot recognizes artificial markers with special shapes and colors in the field of vision through the v...

AI Technical Summary

Problems solved by technology

Although scholars at home and abroad have done a lot of research work on the design and identification of artificial markers, the positioning technology of indoor mobile robots based on artificial markers generally faces the following key problems: (1) Positioning accuracy: the robot must be able to accurately realize Self-positioning, so as to guide the next action and improve the positioning accuracy of the robot, is the primary problem of mobile robot positioning; (2) Real-time problem: During the positioning process of the mobile robot, it must be able to perform self-positioning in real time to ensure that the robot can quickly make dynamic decisions ;(3) Robustness problem: when the mobile robot recognizes and locates the markers, it must have sufficient ability to overcome external environmental interference such as light, and improve the robustness of positioning

[0004] Most of the existing indoor mobile robot visual positioning methods are based on the Apriltag artificial labeling system developed by the April Laboratory of Michigan State University. It takes a long time to complete the recognition and positioning of a frame of pictures containing complete labels.

The core idea of ​​the existing label recognition is to cluster the edge points according to the gradient difference first, then fit the edge line, and then obtain a closed quadrilateral according to the fitted line segment, judge whether the quadrilateral is a label, and finally decode and locate the system. It takes a lot of time and resources to traverse the background information other than the labels in the picture, and usually there are many straight line features in the background, which undoubtedly increases the processing time of the system

Images