基于深度特征的单目视觉惯导里程计

徐伟锋; 蔡述庭; 熊晓明

doi:10.12052/gdutxb.210028

欢迎来到能源电力期刊网！

English Version 期刊登录

您当前的位置：

首页 >

文章列表页 >

基于深度特征的单目视觉惯导里程计

更新时间：2026-05-27

- 基于深度特征的单目视觉惯导里程计
- Visual Inertial Odometry Based on Deep Features
- 广东工业大学学报 2023年40卷第1期页码：56-60, 76
- 作者机构：
  
  广东工业大学自动化学院,广东,广州,510006
- 作者简介：
  
  徐伟锋(1996–) ，男，硕士研究生，主要研究方向为计算机视觉、深度学习等
  蔡述庭(1979–) ，男，教授，博士，主要研究方向为FPGA加速、深度学习等，E-mail：shutingcai@126.com
- 基金信息：
  
  广东省应用型科技研发专项(2017B090909004)
- DOI：10.12052/gdutxb.210028
  中图分类号： TP301
- 网络首发：2023-01-25，
  
  纸质出版：2023
- 稿件说明：
移动端阅览
徐伟锋, 蔡述庭, 熊晓明. 基于深度特征的单目视觉惯导里程计[J]. 广东工业大学学报, 2023, 40(1): 56-60, 76.

Xu Wei-feng, Cai Shu-ting, Xiong Xiao-ming. Visual Inertial Odometry Based on Deep Features[J]. 2023, 40(1): 56-60, 76.
徐伟锋, 蔡述庭, 熊晓明. 基于深度特征的单目视觉惯导里程计[J]. 广东工业大学学报, 2023, 40(1): 56-60, 76. DOI： 10.12052/gdutxb.210028.

Xu Wei-feng, Cai Shu-ting, Xiong Xiao-ming. Visual Inertial Odometry Based on Deep Features[J]. 2023, 40(1): 56-60, 76. DOI： 10.12052/gdutxb.210028.

摘要

视觉里程计是SLAM (Simultaneous Localization and Mapping) 领域中的基石，单目视觉里程计因其成本低廉和仅需较少的相机标定工作而占据着重要的地位，但它存在着尺度不确定、尺度漂移、鲁棒性差等缺点。本文在ORB_SLAM3的基础上，提出了一种基于深度特征的单目视觉惯导里程计，简称DF-VIO(Visual Inertial Odometry Based on Deep Features)，它采用深度学习网络提取的深度特征替代传统的人工点特征，并融合了人工线特征，强化了系统在现实复杂场景下的鲁棒性；另外，系统提供了多种位姿跟踪方式，除了基于恒速模型和跟踪参考关键帧的方式外，还提供了一种基于深度学习网络的可重复性图的位姿跟踪方法，进一步提高了系统位姿跟踪的精度。在公开数据集EuRoC上进行对比实验，在纯视觉模式下，平均轨迹误差下降了25.9%，在视觉惯导模式下，平均轨迹误差下降了8.6%，证明了本文提出的系统在复杂的场景下能够具有更高的鲁棒性。

Abstract

Visual odometry is the cornerstone in the field of SLAM. Monocular visual odometry occupies an important position because of its low cost and less camera calibration

but it has some shortcomings such as scale uncertainty

scale drift

poor robustness

and so on. To solve these problems

based on ORB-SLAM3

we process a monocular visual-inertial navigation odometer with depth features

referred to as DF-VIO (Visual Inertial Odometry Based on Deep Features)

which uses depth features extracted by deep learning network to replace traditional artificial point features

and fuses artificial line features to enhance the robustness of the system in real complex scenes. Besides

the system provides a variety of pose tracking methods. In addition to the method based on the constant speed model and tracking reference keyframe

a pose tracking method based on the predicted repeatability map is also provided

which further improves the accuracy of system pose tracking. Comparative experiments are carried out on the open data set EuRoC

and the average trajectory error is reduced by 25.9% in pure visual mode and 8.6% in visual-inertial mode

which proves that the system proposed in this paper can be more robust in complex scenes.

关键词

Keywords

references

CADENA C, CARLONE L, CARRILLO H, et al . Past, present, and future of simultaneous localization and mapping: toward the robust-perception age [J ] . IEEE Transactions on Robotics, 2016, 32(6): 1309-1332.

PARK S, SCHPS T, POLLEFEYS M. Illumination change robustness in direct visual slam[C]//2017 IEEE international conference on Robotics and Automation (ICRA) . Singapore: IEEE, 2017: 4523-4530.

CHI P K, SU C Y. A Research on monocular visual odometry for mobile robots [J]. Journal of Guangdong University of Technology, 2017, 34(5): 40-44.

RU S N, HE Y L, YE X Y. Visual odometry based on sparse direct method loop-closure detection [J]. Journal of Guangdong University of Technology, 2021, 38(3): 48-54.

STRASDAT H, MONTIEL J, DAVISON A J. Scale drift-aware large scale monocular SLAM[C]// Robotics: Science and Systems VI. Zaragoza: MIT Press, 2010.

MUR-ARTAL R, TARDÓS J D. Visual-inertial monocular SLAM with map reuse [J]. IEEE Robotics and Automation Letters, 2017, 2(2): 796-803.

FORSTER C, CARLONE L, DELLAERT F, et al . On-manifold preintegration for real-time visual-inertial odometry [J ] . IEEE Transactions on Robotics, 2016, 33(1): 1-21.

QIN T, SHEN S. Online temporal calibration for monocular visual-inertial systems[C]//2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) . Madrid: IEEE, 2018: 3662-3669.

LONG J, SHELHAMER E, DARRELL T. Fully convolutional networks for semantic segmentation[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Boston: IEEE, 2015: 3431-3440.

EIGEN D, FERGUS R. Predicting depth, surface normals and semantic labels with a common multi-scale convolutional architecture[C]//Proceedings of the IEEE International Conference on Computer Vision. Santiago: IEEE, 2015: 2650-2658.

TORRES-CAMARA J M, ESCALONA F, GOMEZ-DONOSO F, et al. Map slammer: densifying scattered KSLAM 3D maps with estimated depth[C]//Iberian Robotics Conference. Porto: Springer, Cham, 2019: 563-574.

YANG S, SCHERER S. Cubeslam: monocular 3-D object SLAM [J]. IEEE Transactions on Robotics, 2019, 35(4): 925-938.

GRINVALD M, FURRER F, NOVKOVIC T, et al . Volumetric instance-aware semantic mapping and 3D object discovery [J ] . IEEE Robotics and Automation Letters, 2019, 4(3): 3037-3044.

DETONE D, MALISIEWICZ T, RABINOVICH A. Superpoint: self-supervised interest point detection and description[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops. Salt Lake City: IEEE, 2018: 224-236.

GROMPONE VON GIOI R, JAKUBOWICZ J, MOREL J M, et al . LSD: a fast line segment detector with a false detection control [J ] . IEEE Transactions on Pattern Analysis and Machine Intelligence, 2008, 32(4): 722-732.

HUANG H, YE H, SUN Y, et al. Monocular visual odometry using learned repeatability and description[C]//2020 IEEE International Conference on Robotics and Automation (ICRA) . Paris: IEEE, 2020: 8913-8919.

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.

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

面向电力场景图像的动态自适应增量目标检测DA-IOD算法

基于域不变判别特征学习的深子域自适应方法

基于主动学习和视觉状态空间模型的热点检测器

基于路况参数的混合动力机车能量管理策略研究

面向灾后救援的多无人机通感算一体化资源分配优化方法