计算机与数字工程2023，Vol.51Issue(11)：2666-2670,5.DOI:10.3969/j.issn.1672-9722.2023.11.035
基于光流和自注意力的视觉里程计方法
Visual Odometry Method Based on Optical Flow and Self-attention
高静 1任明武1
作者信息
- 1. 南京理工大学计算机科学与工程学院 南京 210094
- 折叠
摘要
Abstract
As an important part of visual Simultaneous Localization and Mapping(SLAM),visual odometry is widely used in fields such as unmanned driving and mobile robots.In order to make up for the shortcomings of the existing methods,this paper pro-poses an end-to-end visual odometry method based on optical flow and self-attention.First,the method introduces the advanced op-tical flow estimation RAFT model to extract optical flow rich in motion information.Secondly,the relationship between image se-quences is learned by combining Bi-LSTM.Finally,drawing on the idea of key frames in traditional methods,the paper introduces self-attention mechanism and the relative pose between the last two frames of images is obtained through the characteristics of con-secutive multiple frames.Experimental results show that the method significantly reduces the root mean square error of rotation and translation.关键词
视觉里程计/光流/双向长短期记忆网络/自注意力机制Key words
visual odometry/optical flow/Bi-LSTM/self-attention分类
信息技术与安全科学引用本文复制引用
高静,任明武..基于光流和自注意力的视觉里程计方法[J].计算机与数字工程,2023,51(11):2666-2670,5.
