智能科学与技术学报 ›› 2021, Vol. 3 ›› Issue (4): 482-491.doi: 10.11959/j.issn.2096-6652.202148

• 学术论文 • 上一篇    下一篇

基于改进M-ORB的视觉SLAM直接-闭环检测算法

李伟1,2, 任孟瀚1,2, 黄威豪1,3, 杜晓玉1,2, 周毅1,3   

  1. 1 河南大学计算机与信息工程学院,河南 开封475004
    2 河南省车联网协同技术国际联合实验室,河南 开封 475004
    3 鹰驾科技(深圳)有限公司,广东 深圳518052
  • 修回日期:2021-02-26 出版日期:2021-12-15 发布日期:2021-12-01
  • 作者简介:李伟(1979- ),女,河南大学计算机与信息工程学院副教授,主要研究方向为机器人导航、运动规划和控制
    任孟瀚(1997- ),男,河南大学计算机与信息工程学院硕士生,主要研究方向为机器人导航控制、路径规划
    黄威豪(1996- ),男,河南大学计算机与信息工程学院硕士生,主要研究方向为机器人导航控制、图像处理
    杜晓玉(1979- ),女,博士,河南大学计算机与信息工程学院副教授,主要研究方向为无线传感器网络定位及覆盖技术
    周毅(1981- ),男,博士,河南大学计算机与信息工程学院教授、博士生导师,河南省车联网协同技术国际联合实验室主任,主要研究方向为机器人导航控制、车联网技术
  • 基金资助:
    国家自然科学基金资助项目(61701170);河南省科技发展计划项目(202102210327);河南省科技发展计划项目(202102310198);河南省科技发展计划项目(202102210412)

Improved M-ORB based direct-loop closure detection algorithm for visual SLAM

Wei LI1,2, Menghan REN1,2, Weihao HUANG1,3, Xiaoyu DU1,2, Yi ZHOU1,3   

  1. 1 School of Computer and Information Engineering, Henan University, Kaifeng 475004, China
    2 International Joint Research Laboratory for Cooperative Vehicular Networks of Henan, Kaifeng 475004, China
    3 Eagle Drive Technology (Shenzhen) Co., Ltd., Shenzhen 518052, China
  • Revised:2021-02-26 Online:2021-12-15 Published:2021-12-01
  • Supported by:
    The National Natural Science Foundation of China(61701170);The Program for Science and Technology Development of Henan Province(202102210327);The Program for Science and Technology Development of Henan Province(202102310198);The Program for Science and Technology Development of Henan Province(202102210412)

摘要:

直接法SLAM不在前端提取图像特征点,使得后端无法生成视觉词袋,这导致大部分直接法SLAM无法使用带有词袋模型的闭环检测来消除系统的累积误差。针对此问题,提出一种基于改进M-ORB的视觉SLAM直接-闭环检测算法,生成闭环检测所需的词袋模型,然后采用词频-逆文档频率算法对视觉词典树各个子节点中的视觉单词进行自适应分配权重,得到场景信息的准确表述。在TUM、KITTI两种公开数据集上进行了对比实验,实验结果表明,所提出的算法能够有效检测到闭环,并在不降低准确性的同时,提高SLAM的实时性与鲁棒性。

关键词: 视觉SLAM, 闭环检测, 词袋模型, 词频-逆文档频率

Abstract:

Most kinds of direct methods do not extract image feature points in the front end of SLAM system, resulting in that they cannot use loop closure detection with bag-of-words models to eliminate the cumulative error of the system.To resolve this problem, an improved mature-oriented fast and rotated BRIEF (M-ORB) based direct-loop closure detection algorithm for visual SLAM was proposed, which designed an improved M-ORB, generated the bag of words model required for loop closure detection, and then used the term frequency-inverse document frequency (TF-IDF) algorithm to adaptively assign weights to the visual words in each sub-node of the dictionary tree.Finally, an accurate representation of the scene information was obtained.In the end, the proposed algorithm and conducted comparative experiments were verified though two public data sets TUM and KITTI.The experimental results show that the algorithm proposed in this paper can effectively detect the loop closure, and has better real-time and robustness performance without reducing the accuracy.

Key words: visual SLAM, loop closure detection, bag of words model, term frequency-inverse document frequency

中图分类号: 

No Suggested Reading articles found!