融合点线特征与地磁约束的视觉惯性SLAM方法

doi:10.13474/j.cnki.11-2246.2026.0216

测绘通报 ›› 2026, Vol. 0 ›› Issue (2): 97-103.doi: 10.13474/j.cnki.11-2246.2026.0216

融合点线特征与地磁约束的视觉惯性SLAM方法

王耀辉^1,2, 张祖浩^1,2, 陈国良^1,2, 王腾^1,2

1. 自然资源部国土环境与灾害检测重点实验室, 江苏徐州 221116;
2. 中国矿业大学环境与测绘学院, 江苏徐州 221116

收稿日期:2025-06-12 发布日期:2026-03-12
通讯作者: 陈国良。E-mail:chglcumt@163.com
作者简介:王耀辉(1999—),男,硕士生,主要研究方向为室内定位方向。E-mail:TS23160037A31@cumt.edu.cn
基金资助:
国家自然科学基金(42274048);深地国家科技重大专项(2024ZD100410105)

Integrating point-line features and geomagnetic constraints in visual-inertial SLAM

WANG Yaohui^1,2, ZHANG Zuhao^1,2, CHEN Guoliang^1,2, WANG Teng^1,2

1. Key Lab of Land, Environment and Disaster Monitoring, Ministry of Natural Resources, Xuzhou 221116, China;
2. School of Environment and Spatial Informatics, China University of Mining and Technology, Xuzhou 221116, China

Received:2025-06-12 Published:2026-03-12

摘要/Abstract

摘要： 针对传统视觉惯性同步定位与建图算法(VI-SLAM)在复杂条件下定位漂移严重、回环检测误检、漏检率高的问题,本文提出了一种结合点线特征提取与地磁优化的SLAM方法。该方法在现有视觉惯性里程计(VIO)中引入线特征提取方法Fast-EDLines,在计算中使用AVX2指令集加速计算并采取长线段合并与短线段剔除策略,提高线特征提取效率;同时,在回环检测中融合九轴IMU中磁力计数据,利用地磁约束并结合关键帧暂存缓冲区策略,动态调整视觉匹配阈值,减少误检、漏检率。将该算法在公开数据集VECtor Benchmark中开展测试,相较于传统VINS-Mono和PL-VINS,定位精度分别提升7.0和2.9倍,有效提升了SLAM算法在复杂环境下的定位精度与稳健性。

关键词: 视觉惯性SLAM, 点线特征检测, 地磁序列匹配, 回环检测

Abstract: To address the problems of severe localization drift and high false positive/negative rates in loop closure detection under complex conditions in traditional visual-inertial simultaneous localization and mapping (VI-SLAM)systems,we propose a SLAM method that integrates point-line feature extraction and geomagnetic optimization.On one hand,the efficient line feature extraction algorithm Fast-EDLines is introduced into the existing visual-inertial odometry (VIO),accelerated using the AVX2 instruction set,along with a strategy of merging long line segments and eliminating short ones.On the other hand,in the loop closure detection process,magnetometer data from a 9-axis IMU is fused to apply geomagnetic constraints.Combined with a keyframe temporary buffer strategy,the visual matching threshold is dynamically adjusted to reduce false detections and missed detections.The proposed algorithm is tested on the public dataset VECtor Benchmark,and results show that the localization accuracy is improved by 7.0 times and 2.9 times compared to VINS-Mono and PL-VINS,respectively.Effectively improve the positioning accuracy and robustness of SLAM algorithm in complex environments.

Key words: visual-inertial SLAM, point-line feature detection, geomagnetic sequence matching, loop closure detection

中图分类号:

P228

王耀辉, 张祖浩, 陈国良, 王腾. 融合点线特征与地磁约束的视觉惯性SLAM方法[J]. 测绘通报, 2026, 0(2): 97-103.

WANG Yaohui, ZHANG Zuhao, CHEN Guoliang, WANG Teng. Integrating point-line features and geomagnetic constraints in visual-inertial SLAM[J]. Bulletin of Surveying and Mapping, 2026, 0(2): 97-103.

参考文献

[1] 陈锐志,陈亮.基于智能手机的室内定位技术的发展现状和挑战[J].测绘学报,2017,46(10):1316-1326.
[2] 王怡欣,刘晖,钱闯,等.一种基于智能手机的实时高精度定位系统开发与车载应用测试[J].测绘通报,2022(10):56-61.
[3] 王腾,毕京学,陈国良,等.信道状态信息无线感知数据获取及应用综述[J].导航定位与授时,2024,11(1):10-29.
[4] 束明聪.基于地磁和惯性增强感知的室内视觉定位关键技术研究[D].徐州:中国矿业大学,2023.
[5] 李由.基于MEMS惯性传感器、WiFi、磁场特征的移动智能终端室内行人导航算法[D].武汉:武汉大学,2015.
[6] YOUSIF K,BAB-HADIASHAR A,HOSEINNEZHAD R.An overview to visual odometry and visual SLAM:applications to mobile robotics[J].Intelligent Industrial Systems,2015,1(4):289-311.
[7] 范启亮,丁度坤.基于多特征信息定位的机器人视觉SLAM算法[J].测绘通报,2025(4):14-19.
[8] LI Jinyu,YANG Bangbang,CHEN Danpeng,et al.Survey and evaluation of monocular visual-inertial SLAM algorithms for augmented reality[J].Virtual Reality & Intelligent Hardware,2019,1(4):386-410.
[9] 曾攀,潘树国,黄砺枭,等.基于加权预积分和快速初始化的惯性辅助单目前端模型[J].测绘通报,2019(8):8-13.
[10] MOURIKIS A I,ROUMELIOTIS S I.A multi-state constraint Kalman filter for vision-aided inertial navigation[J].Proceedings of 2007 IEEE International Conference on Robotics and Automation.[S.l.]:IEEE,2007:3565-3572.
[11] 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.
[12] FU Qiang,WANG Jialong,YU Hongshan,et al.PL-VINS:real-time monocular visual-inertial SLAM with point and line features[EB/OL].[2025-06-10]https://arxiv.org/abs/2009.07462.
[13] WILLIAMS B,CUMMINS M,NEIRA J,et al.A comparison of loop closing techniques in monocular SLAM[J].Robotics and Autonomous Systems,2009,57(12):1188-1197.
[14] GALVEZ-LÓPEZ D,TARDOS J D.Bags of binary words for fast place recognition in image sequences[J].IEEE Transactions on Robotics,2012,28(5):1188-1197.
[15] MUR-ARTAL R,MONTIEL J M M,TARDÓS J D.ORB-SLAM:a versatile and accurate monocular SLAM system[J].IEEE Transactions on Robotics,2015,31(5):1147-1163.
[16] AKINLAR C,TOPAL C.EDLines:a real-time line segment detector with a false detection control[J].Pattern Recognition Letters,2011,32(13):1633-1642.
[17] DESOLNEUX A,MOISAN L,MOREL J M.from gestalt theory to image analysis:a probabilistic approach[M].New York:Springer New York,2008.
[18] GAO Ling,LIANG Yuxuan,YANG Jiaqi,et al.VECtor:a versatile event-centric benchmark for multi-sensor SLAM[J].IEEE Robotics and Automation Letters,2022,7(3):8217-8224.

融合点线特征与地磁约束的视觉惯性SLAM方法

Integrating point-line features and geomagnetic constraints in visual-inertial SLAM

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 3

编辑推荐

Metrics

本文评价

[1]	郝春霆, 刘飞, 王坚, 韩厚增, 李艳东. 复杂场景下基于关键帧选取与回环约束的视觉/惯性导航算法[J]. 测绘通报, 2025, 0(4): 20-26.
[2]	范军林, 肖斌, 涂梨平, 胡全一, 师现杰, 危双丰. RGB-D SLAM在室内高精度三维测图中的应用[J]. 测绘通报, 2021, 0(8): 119-122.
[3]	张良桥, 陈国良, 许晓东, 连达军, 王睿. 一种用于图像特征提取的改进ORB-SLAM算法[J]. 测绘通报, 2019, 0(3): 16-20.