融合点线特征的视觉惯性同时定位及建图

姚建均; 李英朝; 吴杨; 唐瑞卓; 于新达; 闫宇坤

doi:10.11990/jheu.202209031

Chinese

您当前的位置：

首页 >

文章列表页 >

融合点线特征的视觉惯性同时定位及建图

更新时间：2025-09-01

- 融合点线特征的视觉惯性同时定位及建图
- Visual-inertia simultaneous localization and mapping based on point-and-line features
- 哈尔滨工程大学学报 2024年45卷第4期页码：771-778
- 作者机构：
  
  1.哈尔滨工程大学机电工程学院, 黑龙江哈尔滨 150001
  2.维沃移动通信有限公司, 广东东莞 523850
- 作者简介：
  
  [ "姚建均, 男, 教授, 博士生导师" ]
- 基金信息：
  
  黑龙江省自然科学基金项目(E2018019)
- DOI：10.11990/jheu.202209031
  中图分类号： TP242.6
- 收稿：2022-09-14，
  
  网络首发：2023-09-11，
  
  纸质出版：2024-04-05
- 稿件说明：
移动端阅览
姚建均, 李英朝, 吴杨, 等. 融合点线特征的视觉惯性同时定位及建图[J]. 哈尔滨工程大学学报, 2024,45(4):771-778.

Jianjun YAO, Yingzhao LI, Yang WU, et al. Visual-inertia simultaneous localization and mapping based on point-and-line features[J]. Journal of Harbin Engineering University, 2024, 45(4): 771-778.
姚建均, 李英朝, 吴杨, 等. 融合点线特征的视觉惯性同时定位及建图[J]. 哈尔滨工程大学学报, 2024,45(4):771-778. DOI： 10.11990/jheu.202209031.

Jianjun YAO, Yingzhao LI, Yang WU, et al. Visual-inertia simultaneous localization and mapping based on point-and-line features[J]. Journal of Harbin Engineering University, 2024, 45(4): 771-778. DOI： 10.11990/jheu.202209031.

摘要

为了解决移动机器人在低纹理场景中的定位精度较低且容易跟踪丢失问题

本文设计了一种点线特征提取和匹配策略

并以此构建了视觉惯性同时定位和建图系统。提出线特征提取和匹配算法

通过改良线特征提取算法的隐藏参数

提高了线特征提取的精度。利用点线特征不同匹配筛选框架减少误匹配的数目

得出了可以应用于视觉惯性同时定位和建图系统的线特征提取匹配算法。在现有视觉惯性框架中引入提出的线特征约束

搭建了能在未知低纹理环境下鲁棒运行的视觉惯性同时定位及建图系统。研究表明: 在真实环境中的移动机器人定位实验证明了该系统的精度和鲁棒性优于现有的视觉惯性框架

其室内定位精度提高了24.2%

走廊定位精度提高了8%

对于移动机器人在低纹理场景下的高精度定位具有较高价值。

Abstract

The accuracy of mobile robot localization in low-texture scenes is often compromised

leading to frequent tracking loss. To solve this problem

this study proposes an innovative point-line feature extraction and matching strategy incorporated into the visual-inertial simultaneous localization and mapping (SLAM) system. The approach begins by proposing a line feature extraction and matching algorithm. Refining the hidden parameters of the line feature extraction algorithm improves accuracy. Subsequently

diverse matching screening frameworks for point-line features are employed to reduce mismatches. This approach results in a line feature extraction matching algorithm suitable for the visual-inertial SLAM system. By integrating the proposed line feature constraint into the current visual-inertial framework

this study establishes a robust visual-inertial SLAM system suitable for operation in unknown low-texture environments. Experimental validation with a mobile robot in a real-world setting demonstrates superior accuracy and robustness of the proposed strategy compared with those of the existing visual-inertial framework. The system enhances indoor localization accuracy by 24.2% and corridor localization accuracy by 8%

providing substantial value for high-precision mobile robot localization in low-texture scenes.

关键词

Keywords

references

TOURANI A, BAVLE H, SANCHEZ-LOPEZ J, et al. Visual SLAM: What are the current trends and what to expect[J]. Sensors, 2022, 22(23): 9297-9315.

王立鹏, 张佳鹏, 张智, 等. 基于深度学习的移动机器人语义SLAM方法研究[J]. 哈尔滨工程大学学报, 2024, 45(2): 306-313.

WANG Lipeng, ZHANG Jiapeng, ZHANG Zhi, et al. Research on a semantic SLAM method of a mobile robot based on deep learning[J]. Journal of Harbin Engineering University, 2024, 45(2): 306-313.

伍明, 李广宇, 魏振华, 等. 纯方位角目标跟踪及移动平台可观性控制方法[J]. 智能系统学报, 2022, 17(5): 919-930.

WU Ming, LI Guangyu, WEI Zhenhua, et al. Bearing only target tracking and observability control of a mobile robot[J]. CAAI Transactions on Intelligent Systems, 2022, 17(5): 919-930.

陈国军, 陈巍, 郭铁铮, 等. 基于视觉惯性里程计与语义信息的无人机SLAM方法研究[J]. 计算机应用研究, 2022, 39(3): 826-830, 840.

CHEN Guojun, CHEN Wei, GUO Tiezheng, et al. Research on UAV SLAM method based on visual inertial odometer and semantic information[J]. Application research of computers, 2022, 39(3): 826-830, 840.

孙永全, 田红丽. 视觉惯性SLAM综述[J]. 计算机应用研究, 2019, 36(12): 3530-3533, 3552.

SUN Yongquan, TIAN Hongli. Overview of visual inertial SLAM[J]. Application research of computers, 2019, 36(12): 3530-3533, 3552.

肖春亮, 张忠民. 基于改进容积卡尔曼滤波器的超宽带/惯性导航系统室内融合定位技术[J]. 应用科技, 2023, 50(6): 69-75.

XIAO Chunliang, ZHANG Zhongmin. Indoor fusion positioning technology of ultra wide band/inertial navigation system based on improved cubature Kalman filter[J]. Applied science and technology, 2023, 50(6): 69-75.

QIN Tong, LI Peiliang, SHEN Shaojie. VINS-mono: a robust and versatile monocular visual-inertial state estimator[J]. IEEE transactions on robotics, 2018, 34(4): 1004-1020.

朱永成. 基于VINS-MONO的融合SLAM应用于自动驾驶的技术研究[D]. 北京: 北京邮电大学, 2021: 13-18.

ZHU Yongcheng. Research on the application of fusion SLAM in autopilot based on VINS-MONO[D]. Beijing: Beijing University of Posts and Telecommunications, 2021: 13-18.

赵恒飞. 基于改进回环检测的VINS-Mono水下SLAM算法研究[D]. 杭州: 浙江大学, 2021: 25-30.

ZHAO Hengfei. Research on underwater VINS-mono SLAM algorithm based on improved loop detection[D]. Hangzhou: Zhejiang University, 2021: 25-30.

KONG Xiaotong, WU Chang, Yuan You, et al. Hybrid Indoor Positioning Method of BLE and Monocular VINS Based Smartphone[J]. IEEE transactions on instrumentation and measurement, 2023.

WANG Zhiheng, WU Fuchao, HU Zhanyi. MSLD: a robust descriptor for line matching[J]. Pattern recognition, 2009, 42(5): 941-953.

SOLÀ J, VIDAL-CALLEJA T, CIVERA J, et al. Impact of landmark parametrization on monocular EKF-SLAM with points and lines[J]. International journal of computer vision, 2012, 97(3): 339-368.

GOMEZ-OJEDA R, BRIALES J, GONZALEZ-J J. PL-SVO: Semi-direct Monocular Visual Odometry by combining points and line segments[C]//2016 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). Piscataway, 2016: 4211-4216.

GOMEZ-OJEDA R, MORENO F, ZUÑIGA D, et al. PL-SLAM: A stereo SLAM system through the combination of points and line segments[J]. IEEE transactions on robotics, 2019, 35(3): 734-746.

GROMPONE V R, JAKUBOWICZ J, MOREL J, et al. LSD: A fast line segment detector with a false detection control[J]. IEEE transactions on pattern analysis and machine intelligence, 2010, 32(4): 722-732.

付煜, 郑爽, 别桐, 等. 融合点线特征的视觉惯性SLAM算法[J]. 计算机应用研究, 2022, 39(2): 349-355.

FU Yu, ZHENG Shuang, BIE Tong, et al. Visual inertial SLAM algorithm fusing point and line feature[J]. Application research of computers, 2022, 39(2): 349-355.

袁梦, 李艾华, 郑勇, 等. 点线特征融合的单目视觉里程计[J]. 激光与光电子学进展, 2018, 55(2): 021501.

YUAN Meng, LI Aihua, ZHENG Yong, et al. Point-line feature fusion in monocular visual odometry[J]. Laser&optoelectronics progress, 2018, 55(2): 021501.

ZHANG Lilian, KOCH R. An efficient and robust line segment matching approach based on LBD descriptor and pairwise geometric consistency[J]. Journal of visual communication and image representation, 2013, 24(7): 794-805.

樊逸清. 优化特征点匹配的多单应变换方法[D]. 上海: 华东师范大学, 2019: 21-29.

FAN Yiqing. Multi-homography transformation method for optimizing feature correspondence[D]. Shanghai: East China Normal University, 2019: 21-29.

佟强, 王紫瑶, 杨大利, 等. 利用单应变换与对极约束的基础矩阵估计算法[J]. 郑州大学学报(理学版), 2021, 53(1): 61-67.

TONG Qiang, WANG Ziyao, YANG Dali, et al. Fundamental matrix estimation using homography transformation and epipolar geometry[J]. Journal of Zhengzhou University (natural science edition), 2021, 53(1): 61-67.

郭迎, 赵祥模, 梁睿琳, 等. 双目视觉下的自动驾驶车辆多类型障碍物感知[J]. 哈尔滨工程大学学报, 2023, 44(8): 1406-1411.

GUO Ying, ZHAO Xiangmo, LIANG Ruilin, et al. Perception of multiple types of obstacles in autonomous vehicles under binocular vision[J]. Journal of Harbin Engineering University, 2023, 44(8): 1406-1411.

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

基于轨道不平顺匹配的多源融合列车定位方法

双目视觉下的自动驾驶车辆多类型障碍物感知