计算机应用研究2018，Vol.35Issue(1)：1-6,6.DOI:10.3969/j.issn.1001-3695.2018.01.001
基于单目视觉的同时定位与建图算法研究综述
Survey on monocular visual SLAM algorithms
摘要
Abstract
Compared with traditional laser scanner based SLAM method,camera based SLAM algorithms outperformed in cost as well as information,and could make mobile robot smarter.Instead of using 3D sensors,monocular visual SLAM utilized 2D image sequence to reconstruct 3D map and performed real-time localization.This paper aimed at providing a survey on monocular visual SLAM algorithms.It studied the most popular visual SLAM algorithms in the last decade and discussed the main principle and their classification.Then it pointed out that the optimization method would be the mainstream.It summarized the principle and practice of the state of the art visual SLAM or visual Odometry systems from the angle of initialization,pose estimation,map generation and loop closure.According to above,this paper also elaborated the design scheme and performance of the state of art monocular SLAM algorithms.At last,it concluded with the viewpoint for the research trend.关键词
单目相机/视觉定位/视觉里程计/视觉同时定位与建图Key words
monocular camera/visual localization/visual odometry/visual SLAM (simultaneous localization and mapping)分类
信息技术与安全科学引用本文复制引用
朱凯,刘华峰,夏青元..基于单目视觉的同时定位与建图算法研究综述[J].计算机应用研究,2018,35(1):1-6,6.基金项目
国家自然科学基金资助项目(61403202) （61403202）
中国博士后科学基金面上资助项目(2014M561654) （2014M561654）
