Monocular SLAM initialization method and device and electronic equipment

Abstract

The embodiment of the invention provides a monocular SLAM initialization method and device and electronic equipment, and belongs to the technical field of image processing. The method comprises the following steps: acquiring multiple frames of continuous images collected by a target camera; calculating a homography matrix among multiple frames of continuous images; obtaining a homography matrix between every two images by using the homography matrix between the multiple frames of continuous images; and obtaining pose data and a plane normal vector of the target camera according to all the homography matrix optimization variables. In the initialization process, multi-frame information is used, and an original method for solving the camera pose and the plane normal vector through matrix decomposition is replaced with variable optimization. According to the method, the parameter quantity is small, the camera pose and the plane normal direction are calculated by using the result of variable optimization, the spatial position of the feature point is calculated by using the plane normal direction and the normalized distance from the camera to the plane, triangularization and PnP are avoided, and the efficiency of monocular SLAM initialization is improved.

Description

technical field [0001] The present disclosure relates to the technical field of image processing, and in particular to a monocular SLAM initialization method, device and electronic equipment. Background technique [0002] Simultaneous Localization and Mapping (SLAM for short), also known as Concurrent Mapping and Localization (CML for short), refers to placing a robot in an unknown location in an unknown environment. The robot gradually draws a complete map of the environment while moving. The so-called complete map (a consistent map) means that it can travel to every corner of the room without obstacles. The existing monocular SLAM method mainly uses two frames of image information, calculates the camera pose through matrix decomposition, and then calculates the spatial position of the feature points through triangulation, and then uses the PnP and SfM methods to calculate the camera pose and feature Points are optimized to complete the initialization task of SLAM. [000...

AI Technical Summary

Problems solved by technology

[0003] The existing monocular SLAM method has a non-unique answer to matrix decomposition, which requires some selection strategies, and each selection strategy cannot satisfy all situations. The SfM method has many variables, so the convergence speed is slow, and the triangulation and PnP methods need There is a large baseline between the two frames, otherwise technical problems such as degradation will occur

Images