基于改进ORB-SLAM2算法的动态特征点剔除

doi:10.19640/j.cnki.jtau.2024.01.016

天津农学院学报 ›› 2024, Vol. 31 ›› Issue (1): 88-94.doi: 10.19640/j.cnki.jtau.2024.01.016

基于改进ORB-SLAM2算法的动态特征点剔除

周晓睿, 杨磊^通信作者, 娄莉娟, 宋欣, 陈江涛

天津农学院工程技术学院,天津 300392

收稿日期:2023-04-21 出版日期:2024-02-29 发布日期:2024-04-02
通讯作者: 杨磊（1980—）,女,副教授,硕士,主要从事智能农机装备研发与应用。E-mail：yanglei2016@tjau.edu.cu。
作者简介:周晓睿（1999—）,女,硕士在读,主要从事视觉SLAM的研究。E-mail：zhouxiaorui6881@163.com。
基金资助:
天津农学院研究生科研创新项目（2021XY007）; 天津市中央引导地方科技发展基金优秀农业科技特派员项目（22ZYCGSN00660）

Dynamic feature point elimination based on improved ORB-SLAM2

Zhou Xiaorui, Yang Lei^{Corresponding Author}, Lou Lijuan, Song Xin, Chen Jiangtao

College of Engineering and Technology, Tianjin Agricultural University, Tianjin 300392, China

Received:2023-04-21 Online:2024-02-29 Published:2024-04-02

摘要/Abstract

摘要： 随着SLAM系统的不断发展,人们对定位服务的要求越来越高,提高定位精度是一直以来不断研究的课题。为了能以更高定位精度的方式来获取图像中的语义信息,本文首先通过对比One stage算法中的网络模型选用了YOLOV5网络模型对目标物体进行检测和识别,提出一种基于动态区域内剔除动态特征点的SLAM算法,利用训练的网络提取图像中语义信息并对动态目标特征点进行剔除,在公开TUM数据集上进行验证,通过对比真实轨迹和本文算法的估计轨迹来进行误差分析。试验结果表明,本文提出的改进算法相对位移误差的均方根误差减小了97.83%,相对旋转误差的均平方根误差减小了96.80%。

关键词: ORB-SLAM2, 目标检测, 语义信息, SLAM系统, 动态区域

Abstract: With the continuous development of SLAM system, people have higher and higher requirements for location services, and improving location accuracy is always a topic of constant research. In order to obtain the semantic information in the image with higher positioning accuracy, the YOLOV5 network model was first selected to detect and recognize the target object by comparing the network model in One stage algorithm. In this paper, a SLAM algorithm based on dynamic region culling was proposed, which used the trained network to extract the semantic information in the image and cull the feature points of the dynamic target. The algorithm was verified on the open TUM data set, and the error analysis was carried out by comparing the real trajectory with the estimated trajectory of the algorithm in this paper. Experimental results showed that the root mean square error of relative displacement error and the mean square root error of relative rotation error of the proposed algorithm were reduced by 97.83% and 96.80% respectively.

Key words: ORB-SLAM2, object detection, semantic information, SLAM system, dynamic region

中图分类号:

TP391

周晓睿, 杨磊, 娄莉娟, 宋欣, 陈江涛. 基于改进ORB-SLAM2算法的动态特征点剔除[J]. 天津农学院学报, 2024, 31(1): 88-94.

Zhou Xiaorui, Yang Lei, Lou Lijuan, Song Xin, Chen Jiangtao. Dynamic feature point elimination based on improved ORB-SLAM2[J]. Journal of Tianjin Agricultural University, 2024, 31(1): 88-94.

导出引用管理器 EndNote|Reference Manager|ProCite|BibTeX|RefWorks

链接本文: http://xuebao.tjau.edu.cn/CN/10.19640/j.cnki.jtau.2024.01.016

http://xuebao.tjau.edu.cn/CN/Y2024/V31/I1/88

参考文献

[1] 吴涛. 用于移动机器人的视觉SLAM综述[J]. 数据通信,2022(1):48-51.
[2] YADAV R,KALA R.Fusion of visual odometry and place recognition for SLAM in extreme conditions[J]. Applied Intelligence,2022,52(10):11928-11947.
[3] ZHANG L,ZHANG Y J.Improved feature point extraction method of ORB-SLAM2 dense map[J]. Assembly Sutomation,2022,42(4):552-566.
[4] MUR-ARTAL R,MONTIEL J M M,TARDOS J D. ORB-SLAM:A versatile and accurate monocular SLAM system[J]. IEEE Transactions on Robotics,2015,31(5):1147-1163.
[5] CHEN W F,SHANG G T,HU K, et al.A monocular- visual SLAM system with semantic and optical-flow fusion for indoor dynamic environments[J]. Micromachines,2022,13(11):2006.
[6] LOU L,LI Y T,ZHANG Q,et al.SLAM and 3D semantic reconstruction based on the fusion of lidar and monocular vision[J]. Sensors,2023,23(3):1502.
[7] FORSTER C,ZHANG Z,GASSNER M,et al.SVO:Semidirect visual odometry for monocular and multicamera systems[J]. IEEE Transactions on Robotics,2017,33(2):249-265.
[8] MUR-ARTAL R,TARDOS J D.ORB-SLAM2:An open-source SLAM system for monocular, stereo, and RGB-D cameras[J]. IEEE Transactions on Robotics,2017,33(5):1255-1262.
[9] LEI Y,GARDNER A,AGRAM P.Autonomous repeat image feature tracking (autoRIFT) and its application for tracking ice displacement[J]. Remote Sensing,2021,13(4):749.
[10] YOUNG M,PRETTY C,MCCULLOCH J,et al.Sparse point cloud registration and aggregation with mesh-based generalized iterative closest point[J]. Journal of Field Robotics,2021,38(8):1078-1091.
[11] CAMPOS C,ELVIRA R,RODRIGUEZ J G,et al.ORB-SLAM3:An accurate open-source library for visual, visual-inertial,and multimap SLAM[J]. IEEE Transactions on Robotics,2021,37(6):1874-1890.
[12] LIU J D,MEGHADA H S,ZHOU T,et al.An image-aided sparse point cloud registration strategy for managing stockpiles in dome storage facilities[J]. Remote Sensing,2023,15(2):504.
[13] XIA L L,MENG Q Y,CHI D R,et al.An optimized tightly-coupled VIO design on the basis of the fused point and line features for patrol robot navigation[J]. Sensors,2019,19(9):2004.
[14] 许德刚,王露,李凡. 深度学习的典型目标检测算法研究综述[J]. 计算机工程与应用,2021,57(8):10-25.
[15] 刘无纪. 基于SSD的无人机图像目标检测算法研究[D]. 芜湖:安徽工程大学,2023.

基于改进ORB-SLAM2算法的动态特征点剔除

Dynamic feature point elimination based on improved ORB-SLAM2

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 13

编辑推荐

Metrics

本文评价

[1]	安瑞钰, 郝志斌. 基于半监督主动学习的小麦叶片病虫害区域分割方法[J]. 天津农学院学报, 2024, 31(2): 87-93.
[2]	马含章, 王淼鑫, 钟拼扬, 刘华, 常若葵, 董晋峰. 视觉识别的生活垃圾分类系统设计[J]. 天津农学院学报, 2023, 30(4): 53-57.
[3]	郑海波, 宋爽, 刘同海. 基于改进Tiny YOLOv3的交通标志检测方法[J]. 天津农学院学报, 2023, 30(2): 62-68.
[4]	何建祥, 宋欣, 朱垲, 宋俊杰, 谢周强. 基于模糊神经网络的温室小气候预测模型[J]. 天津农学院学报, 2023, 30(1): 74-79.
[5]	高佳颀, 吴芳. 基于机器学习的农村水质水色分类研究[J]. 天津农学院学报, 2022, 29(1): 61-65.
[6]	纪思琪, 吴芳, 李乃祥. 基于决策树的蔬菜病害静态预警模型[J]. 天津农学院学报, 2017, 24(2): 77-80.
[7]	李燕杰, 赵娜, 赵平, 张京京. 基于声卡和LabVIEW的虚拟示波器的设计[J]. 天津农学院学报, 2016, 23(1): 51-53.
[8]	王启欣, 邓胜琳. 一种基于计算机图像处理经典算法的染色体边缘检测方法[J]. 天津农学院学报, 2012, 19(1): 42-44.
[9]	赵娜, 赵平, 高轶军. 机器视觉技术在我国现代农业生产中的应用研究[J]. 天津农学院学报, 2015, 22(2): 55-58.
[10]	杨静. 电子商务顾客信息模型的构建[J]. 天津农学院学报, 2013, 20(1): 37-40.
[11]	韦冰, 王颖杰, 李世栋. 高校毕业生派遣及档案去向查询系统的设计与实现[J]. 天津农学院学报, 2013, 20(2): 43-45.
[12]	马国强, 马吉飞, 郭鹏, 宋志恒, 于娜. 改进的医学CT图像K-均值聚类分割算法的实现[J]. 天津农学院学报, 2013, 20(4): 28-35.
[13]	陈成钢, 艾涛. 基于灰度共生矩阵的纹理分析的统计方法[J]. 天津农学院学报, 2014, 21(2): 33-38.