基于深度学习的视觉同时定位与建图研究进展  

Research progress of visual simultaneous localization and mapping based on deep learning

作　　者：张耀 吴一全[1] 陈慧娴 Zhang Yao;Wu Yiquan;Chen Huixian(College of Electronic and Information Engineering,Nanjing University of Aeronautics and Astronautics,Nanjing 211106,China)

机构地区：[1]南京航空航天大学电子信息工程学院,南京211106

出　　处：《仪器仪表学报》2023年第7期214-241,共28页Chinese Journal of Scientific Instrument

基　　金：国家自然科学基金(61573183)项目资助。

摘　　要：随着机器视觉的不断发展,视觉传感器其小巧轻便、价格低廉等优势,使得视觉同时定位与建图(VSLAM)越来越受人们关注,深度学习为处理VSLAM问题提供了新的方法与思路。本文综述了近年来基于深度学习的VSLAM方法。首先回顾了VSLAM的发展历程,系统阐释了VSLAM的基本原理与组成结构。然后从视觉里程计(VO)、回环检测与建图3个方面分析各类基于深度学习的方法,从特征提取与特征匹配、深度估计与位姿估计及关键帧选择等3个部分阐述了深度学习在VO中的应用;基于场景表达方式的不同,总结了几何建图、语义建图及广义建图中的深度学习方法。接着介绍了目前VSLAM常用的各种数据集以及性能评估指标。最后指出了目前VSLAM面临的难题与挑战,展望未来深度学习与VSLAM结合的研究趋势与发展方向。With the continuous development of machine vision,visual sensors has advantages of lightweight and low cost.Thus,visual simultaneous localization and mapping(VSLAM)is attracting more and more attention and becoming a research hotspot.Deep learning has provided new methods and ideas to deal with VSLAM problems.This article reviews the deep learning-based VSLAM methods in recent years.Firstly,the development history of VSLAM is reviewed,and the basic principle and composition structure of VSLAM are systematically explained.Then,various methods based on deep learning are summarized and analyzed from three aspects,including visual odometry(VO),loop closure detection and mapping.The application of deep learning in visual odometry is described in three parts,which are feature extraction and feature matching,depth estimation and pose estimation and keyframes selection.Based on the different manner of scene representation,deep learning-based methods in geometric mapping,semantic mapping and general mapping are summarized.Thirdly,it introduces various datasets and performance evaluation metrics commonly used in VSLAM at present.Finally,the challenges of VSLAM are pointed out,and the future research trends and development directions of combining deep learning with VSLAM are forecasted.

关 键 词：同时定位与建图 机器视觉 深度学习 视觉里程计 回环检测 数据集 评估指标 

分 类 号：TP242.6[自动化与计算机技术—检测技术与自动化装置] TH89[自动化与计算机技术—控制科学与工程]