融合SuperGlue方法的深度单目视觉惯性导航算法

doi:10.13474/j.cnki.11-2246.2024.0220

测绘通报 ›› 2024, Vol. 0 ›› Issue (2): 113-117.doi: 10.13474/j.cnki.11-2246.2024.0220

融合SuperGlue方法的深度单目视觉惯性导航算法

刘亦博¹, 吴传文², 周宗锟¹, 陈华²

1. 武汉大学卫星导航定位技术研究中心, 湖北武汉 430079;
2. 武汉大学测绘学院, 湖北武汉 430079

收稿日期:2023-06-08 出版日期:2024-02-25 发布日期:2024-03-12
作者简介:刘亦博(1998—),男,硕士生,主要研究方向为视觉惯性SLAM。E-mail:yiboliu@whu.edu.cn
基金资助:
国家重点研发计划(2022YFC3005502);湖北省科技重大专项(2022AAA002)

A deep monocular visual-inertial navigation algorithm with SuperGlue

LIU Yibo¹, WU Chuanwen², ZHOU Zongkun¹, CHEN Hua²

1. GNSS Research Center, Wuhan University, Wuhan 430079, China;
2. School of Geodesy and Geomatics, Wuhan University, Wuhan 430079, China

Received:2023-06-08 Online:2024-02-25 Published:2024-03-12

摘要/Abstract

摘要： 针对图像的深度学习方法是解决传统视觉定位算法在复杂环境下特征提取不稳定、跟踪丢失等难题的有效途径。本文在VINS-Mono的基础上引入基于深度学习的SuperPoint特征提取方法和SuperGlue特征匹配方法,建立了一种融合SuperGlue方法的单目视觉惯性导航算法,并采用开源数据集和实际试验数据进行了评估。结果表明,该方法有效提升了复杂环境下单目视觉惯性算法的稳定性和精度,精度提升幅度可达26%。

关键词: 视觉惯性导航, 深度学习, SuperPoint, SuperGlue, VINS-Mono

Abstract: The deep learning method for images is an effective way to solve the problems of unstable feature extraction and tracking loss of traditional visual positioning algorithms in complex environments. In this paper, we propose a visual-inertial navigation algorithm based on VINS-Mono, which using SuperPoint to get feature points and track them by using SuperGlue. And evaluate it using Open-source dataset and real world experiments. Experimental results show that our algorithm has a significant improvement in positioning accuracy and stability compared with VINS-Mono, and the accuracy improvement can reach 26%.

Key words: visual-inertial navigation, deep learning, SuperPoint, SuperGlue, VINS-Mono

中图分类号:

P228
P237

刘亦博, 吴传文, 周宗锟, 陈华. 融合SuperGlue方法的深度单目视觉惯性导航算法[J]. 测绘通报, 2024, 0(2): 113-117.

LIU Yibo, WU Chuanwen, ZHOU Zongkun, CHEN Hua. A deep monocular visual-inertial navigation algorithm with SuperGlue[J]. Bulletin of Surveying and Mapping, 2024, 0(2): 113-117.

参考文献

[1] 王金科,左星星,赵祥瑞,等. 多源融合SLAM的现状与挑战[J]. 中国图象图形学报,2022,27(2): 368-389.
[2] LOWE D G. Object recognition from local scale-invariant features[C]//Proceedings of the 7th IEEE International Conference on Computer Vision. Kerkyra,Greece:IEEE,1999.
[3] BAY H,TUYTELAARS T,VAN GOOL L. SURF: Speeded up robust features[C]// Proceedings of the 9th European Conference on Computer Vision.Graz,Austria:Springer,2006:404-417.
[4] RUBLEE E,RABAUD V,KONOLIGE K,et al. ORB: an efficient alternative to SIFT or SURF[C]// Proceedings of 2011 International conference on computer vision. Barcelona,Spain: IEEE,2011: 2564-2571.
[5] 张良桥,陈国良,许晓东,等. 一种用于图像特征提取的改进ORB-SLAM算法[J]. 测绘通报,2019(3): 16-20.
[6] 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.
[7] LIU Y,XU X,LI F. Image feature matching based on deep learning[C]//Proceedings of 2018 IEEE International Conference on Computer and Communications (ICCC).Chengdu:IEEE,2018.
[8] TIAN Y,FAN B,WU F. L2-Net: deep learning of discriminative patch descriptor in Euclidean space[C]// Proceedings of 2017 IEEE Conference on Computer Vision and Pattern Recognition(CVPR). Honolulu,USA:IEEE,2017: 661-669.
[9] SUN D,YANG X,LIU M Y,et al. PWC-Net: CNNs for optical flow using pyramid,warping,and cost volume[C]// Proceedings of 2018 IEEE Conference on Computer Vision and Pattern Recognition. Lake City,USA:IEEE,2018: 8934-8943.
[10] DETONE D,MALISIEWICZ T,RABINOVICH A.SuperPoint: self-supervised interest point detection and description[C]// Proceedings of 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).Lake City,USA:IEEE,2018: 224-236.
[11] SARLIN P E,DETONE D,MALISIEWICZ T,et al. SuperGlue: learning feature matching with graph neural networks[C]// Proceedings of 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Seattle,USA:IEEE,2020:4937-4946.
[12] LUCAS B D,KANADE T. An iterative image registration technique with an application to stereo vision[C]// Proceedings of 1981 Imaging Understanding Workshop. Washington,DC:[s.n.],1981: 121-130.
[13] CUTURI M. Sinkhorn distances: Lightspeed computation of optimal transport[J]. Advances in Nural Information Processing Systems,2013,26:2292-2300.
[14] FISCHLER M A,BOLLES R C. Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography[J]. Communications of the ACM,1981,24(6): 381-395.
[15] BURRI M,NIKOLIC J,GOHL P,et al. The EuRoC micro aerial vehicle datasets[J]. The International Journal of Robotics Research,2016,35(10): 1157-1163.
[16] HEDBORG J,RINGABY E,FORSSÉN P E,et al. Structure and motion estimation from rolling shutter video[C]// Proceedings of 2011 IEEE International Conference on Computer Vision Workshops (ICCV Workshops). Barcelona,Spain:IEEE,2011: 17-23.
[17] 钱学飞,沈映政,王友昆,等. 一种改进SURF的视觉影像匹配算法[J]. 测绘通报,2021(1): 99-102.
[18] 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.

融合SuperGlue方法的深度单目视觉惯性导航算法

A deep monocular visual-inertial navigation algorithm with SuperGlue

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	陈昶, 张岩, 李坤衡, 杨润泽, 张俊彬, 梁彦荣. 基于高分七号影像自动提取东北黑土区侵蚀沟的方法[J]. 测绘通报, 2024, 0(3): 1-7.
[2]	张兰兰, 王红雷. 基于深度学习的耕地非农化遥感监测与时空分析——以开阳县为例[J]. 测绘通报, 2024, 0(3): 13-18.
[3]	王鸿雁, 车向红, 徐辛超, 徐胜华, 李洪胜. 利用DeepLabv3+模型提取分析街景图像绿视率——以北京三环内为例[J]. 测绘通报, 2024, 0(3): 88-94.
[4]	马锦山, 贾国焕, 张赛, 张炯. 基于多源高分辨率遥感影像的典型自然资源要素提取[J]. 测绘通报, 2024, 0(3): 123-126,150.
[5]	王红雷, 严文璞. 基于深度学习技术的贵州省耕地占用遥感监测[J]. 测绘通报, 2024, 0(3): 134-139.
[6]	刘丽, 李士垚, 王润, 刘少宇, 宋永飞, 牛瑞卿. 联合深度学习与面向对象分析的卫宁北山露天矿山采场信息提取[J]. 测绘通报, 2024, 0(2): 51-57.
[7]	黄应华, 董振川, 李昊, 陈壮, 刘长睿, 张献州. 城市竣工测绘典型要素语义分割PointNet++深度学习模型适用性分析[J]. 测绘通报, 2024, 0(2): 85-89.
[8]	魏德宏, 禤键豪, 杨嘉伟, 张兴福, 余旭. 基于深度BP/ELMAN神经网络的山区GNSS高程转换精度分析[J]. 测绘通报, 2023, 0(9): 113-116,143.
[9]	张宝安, 高小龙, 金仔燕, 马兰花. 甘肃省地表要素遥感解译样本库建设与应用[J]. 测绘通报, 2023, 0(9): 144-149.
[10]	胡荣明, 李鑫, 竞霞, 武建强, 魏青博. YOLOv7在探地雷达B-Scan图像解译中的应用[J]. 测绘通报, 2023, 0(8): 29-33.
[11]	周宝定, 谢沛瑶, 郭文浩, 毛庆洲. 基于激光点云灰度图像的隧道渗水病害检测[J]. 测绘通报, 2023, 0(8): 34-39,90.
[12]	张戬, 高雅. 深度学习遥感影像解译技术在耕地保护中的应用[J]. 测绘通报, 2023, 0(8): 142-145.
[13]	杨盈, 邱芹军, 谢忠, 田苗, 郑诗语, 郑帅. 人在回路学习增强的地理命名实体识别[J]. 测绘通报, 2023, 0(8): 155-160,177.
[14]	钟静, 孙杰, 赖祖龙, 谌一夫. ICESat-2与Sentinel-2数据融合的深度学习浅滩水深测量[J]. 测绘通报, 2023, 0(7): 39-43.
[15]	沈鑫甦, 嵇灵. 面向遥感地类变化检测的U型深度学习神经网络改进方法[J]. 测绘通报, 2023, 0(6): 93-97,103.