Method for realizing semantic SLAM system based on mobile terminal

Abstract

The invention provides a method for realizing a semantic SLAM system based on a mobile terminal and relates to fusion of construction of an SLAM system and point cloud semantic analysis. The method comprises the following steps: 1) solving a camera pose based on an improved FAST and LDB characteristic point method; 2) carrying out back-end optimization to obtain an accurate point cloud position and an accurate camera pose; 3) carrying out loopback detection; 4) constructing a global point cloud map; 5) realizing an augmented reality system by utilizing the SLAM system; 6) realizing 3D point cloud semantic segmentation by utilizing semantic segmentation; and 7) optimizing the semantic SLAM system based on the mobile terminal. Aiming at environmental cognition in flexible indoor and outdoorscenes and augmented reality demands, especially in the fields of unmanned driving, path planning and the like, a solution low in cost and good in performance is obtained, and the method has extensiveapplication value and expansion capability.

Description

technical field [0001] The present invention relates to the integration of SLAM system construction and point cloud semantic analysis, in particular to a method for realizing a semantic SLAM system based on a mobile terminal. Background technique [0002] With the continuous development of artificial intelligence and computer vision technology, more and more cutting-edge technologies are applied to real products. Technologies such as robotics, face recognition, intelligent algorithms, and 3D reconstruction have gradually integrated into people's lives. During the two sessions held in March this year, the government even made robotics and artificial intelligence a key development industry in the next few years. [0003] SLAM technology has good application prospects in the fields of robotics, autonomous driving, virtual and augmented reality. Among many computer vision and artificial intelligence technologies, SLAM research continues to be hot. In recent years, more and more...

AI Technical Summary

Problems solved by technology

First of all, traditional SLAM requires a large amount of calculations, which requires more demanding hardware computing power, and mobile devices are difficult to cope with; second, monocular SLAM also has scale and precision drift (Strasdat, Montiel, A.J.Davison, Scale drift-aware large scalemonocular SLAM, RSS 2006), the error is relatively large, especially when modeling large outdoor scenes, it often fails (Quan Meixiang, Park Songhao, Li Guo. Review of Visual SLAM [J]. Journal of Intelligent Systems, 2016, 11( 6):768-776); Finally, there are relatively few studies that can simultaneously perform environment modeling and semantic segmentation

Images