Fast pose estimation algorithm for point-line feature visual slam system

Abstract

The invention discloses a fast pose estimation algorithm for a point-line feature visual SLAM system, which includes the following steps: step 1, thread-divided point-line feature extraction and grid distribution of features, and assigning line features to pre-drawn points according to the midpoint position In the fixed image frame grid; step 2, map point and map line midpoint sub-thread projection matching, line features that do not match line features are eliminated; step 3, map point and map line midpoint based on step 2 Pose optimization algorithm. The pose estimation algorithm proposed by the present invention is an algorithm used when the point-line feature SLAM system works normally. Through the introduction of point information in the line feature, the complex 4-degree-of-freedom line feature is simplified, so that the point-line feature pose The efficiency of the estimation problem is greatly improved.

Description

technical field [0001] The invention belongs to the field of computer vision, and in particular relates to a fast pose estimation algorithm of a point-line feature visual SLAM system. Background technique [0002] Simultaneous localization and mapping (SLAM) has become more and more important with the development of unmanned driving and drone technology. It refers to the subject equipped with a specific sensor, without the prior information of the environment, to establish a model of the environment during the movement process, and at the same time estimate its own movement. If the camera is used as the sensor, it is called "visual SLAM". [0003] At present, based on the feature method SLAM system, most of them are pure point features. However, from the perspective of processing low-texture scenes and realizing the visualization of the system, pure point features obviously cannot meet the requirements, but the introduction of line features can effectively solve the above ...

AI Technical Summary

Problems solved by technology

However, from the perspective of processing low-texture scenes and realizing the visualization of the system, pure point features obviously cannot meet the requirements, but the introduction of line features can effectively solve the above two problems

[0004] On the other hand, the introduction of line features has the advantage of enhancing the robustness and visibility of the visual SLAM system, but compared with point features, line features have four degrees of freedom (two endpoints each have a pair of x, y coordinates) , which undoubtedly greatly increases the amount of calculation of the system

Images