Monocular SLAM robust initialization method based on multiple frames

Abstract

The invention discloses a monocular SLAM robust initialization method based on multiple frames, and the method comprises the steps: extracting feature points of image frames in an initial video stream, carrying out the mutual matching, screening out matching points, and obtaining an initial matching point pair; screening out a three-view pair according to the initial matching point pair, then screening out matching points in the three-view pair based on a random sampling consensus algorithm of a trifocal tensor, and constructing a three-frame matching graph; solving relative rotation among the image frames according to a double-vision geometric principle; solving global rotation according to relative rotation among the image frames; solving global displacement based on global rotation; integrating the global rotation and the global displacement to obtain an initial pose of each frame, and performing nonlinear optimization adjustment according to the initial pose; calculating depth of field of the feature points, and recovering three-dimensional coordinates of the feature points; according to the method, the convergence speed can be increased, scatter points are reduced, and therefore the precision of the initial map is improved.

Description

technical field [0001] The invention belongs to the technical field of monocular SLAM initialization, and in particular relates to a multi-frame-based monocular SLAM robust initialization method. Background technique [0002] The goal of simultaneous localization and mapping (SLAM) is to reconstruct the unknown environment while estimating the motion trajectory of the camera. The technology is currently widely used in fields such as augmented reality and autonomous driving, and can operate in real time without relying on external infrastructure. [0003] Initialization is the key to monocular SLAM technology. Through initialization, the initial pose of the camera can be obtained and an initial map can be generated to provide support for the subsequent tracking phase. [0004] At present, the academic community mainly uses the incremental motion recovery structure technology (Structure From Motion, SFM) to initialize the monocular SLAM system, mainly using the epipolar geome...

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to overcome the shortcomings of the inability to quickly converge and the existence of "scattered points" in the above-mentioned prior art, and provide a SLAM initialization method that can increase the convergence speed and reduce the appearance of "scattered points", thereby improving the accuracy of the initial map , specifically a multi-frame-based monocular SLAM robust initialization method

Images