A monocular SLAM initialization method and system based on a wheel type encoder

Abstract

The invention discloses a monocular SLAM initialization method and system based on a wheel type encoder, and the method comprises the steps of selecting a first key frame and a second key frame in anSLAM initialization image sequence, carrying out the feature matching, calculating the world coordinate system coordinates of all matching points in the first key frame, and building an initial pointcloud map; and determining the camera pose of the second key frame by using the displacement information of the wheel type encoder, fixing the camera poses of the first key frame and the second key frame during optimization, and not performing local bundling adjustment on the camera poses of the two frames. According to the present invention, the displacement information of the wheel type encoderis combined with the point characteristics of image information of the visual sensor to play a role in information complementation, the camera pose of the second key frame can be determined very accurately, the scale information of the real world is reserved, the positioning precision of the camera is improved, the operation is simplified, and the response speed is increased.

Description

technical field [0001] The invention relates to initialization of synchronous positioning and map construction, in particular to a wheel encoder-based monocular SLAM initialization method and system. Background technique [0002] The goal of Simultaneous Localization and Mapping (SLAM) is to reconstruct the three-dimensional structure of the environment in real time in an unknown environment and simultaneously position the robot itself. Visual SLAM technology infers the orientation of the visual sensor in the unknown environment based on the captured video information, and builds an environmental map at the same time. The basic principle is the principle of multi-view geometry. The goal of visual SLAM is to simultaneously recover the camera motion parameters C corresponding to each frame of image 1 …C m , and the scene 3D structure X 1 …X n ; where each camera motion parameter C i Contains the position and attitude information of the camera, usually expressed as a 3×3 r...

AI Technical Summary

Problems solved by technology

This method can effectively calculate the camera pose of the second frame and a series of initial map points, but it also has the following shortcomings: 1. The calculation of the essential matrix will cause the problem of uncertain scale, that is, the difference between the calculated value and the real value There is a scaling factor, and due to the uncertainty of the scale, the scaling factor is different for each initialization, so multiple measurements of the same true value may have a large deviation, which is a serious problem in some cases , such as the application scenario of a sweeping robot; 2. The error between the measured value and the real value is large

Images