ScholarMate
English简体中文繁體中文
客服热线:400-1616-289
登录注册
会议论文

Attention-based Long-term Modeling for Deep Visual Odometry

Xu, Sangni*; Xiong, Hao; Wu, Qiuxia; Wang, Zhiyong
International Conference on Digital Image Computing - Techniques and Applications (DICTA)2021DOI: 10.1109/DICTA52665.2021.9647140
3阅读
引用收藏
分享

摘要

Visual odometry (VO) aims to determine the positions of a moving camera from an image sequence it acquired. It has been extensively utilized in many applications such as AR/VR, autonomous driving, and robotics. Conventional VO methods largely rely on hand-crafted features and data association that are in fact unreliable and suffering from fast motions. Therefore, learning-based VO utilizes neural networks mapping an image sequence to corresponding camera poses directly. Most existing learning-based methods also integrate with additional Long Short-Term Memory (LSTM) networks to model the temporal context across images, since the camera pose estimation of an image in VO is highly relevant to other images in the same sequence. However, traditional LSTM is limited to model short-term dependency rather than long-term temporal context or global information. To mitigate this issue, we propose an attention based long-term modelling approach by devising a new fusion gate into the LSTM cell. Our method consists of two modules: convolutional motion encoder and recurrent global motion refinement module. Specifically, the convolutional motion encoder extracts from images motion features which are then fused by the refinement module with more long-term temporal information. In the refinement module, the devised fusion gate generates long-term temporal information in two phases: (1) extracting correlated long-term information from previous predictions through a devised attention module; and (2) updating the current hidden state with extracted long-term information. As a result, it enables our model to gather long-term temporal information and further enhance estimation accuracy. We comprehensively evaluate our proposed method on two public datasets, KITTI and Oxford RobotCar. The experimental results demonstrate the effectiveness and superiority of our method over the baseline model.

学科与关键词

关键词
Visual Odometryattentionlong-term modelingLSTM
相关
加载中…
  • Robust visual odometry using sparse optical flow network
    Liu, Qiang; Chen, Baojia*ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE, 2022, 116: 105471.被引 1
  • Deep learning based on LSTM model for enhanced visual odometry navigation system
    Deraz, Ashraf A.*; Badawy, Osama; Elhosseini, Mostafa A.*; Mostafa, Mostafa; Ali, Hesham A.; El-Desouky, Ali I.Ain Shams Engineering Journal, 2023, 14(8): 102050.被引 6
  • Fast Monocular Visual Odometry for Augmented Reality on Smartphones
    Cao, Mingwei*; Zheng, Liping; Jia, Wei; Liu, XiaopingIEEE Consumer Electronics Magazine, 2023, 12(6): 78-84.被引 4
查看全部 →

会议信息

会议名称
International Conference on Digital Image Computing - Techniques and Applications (DICTA)
会议日期
2021-11-29 至 2021
论文集名
2021 INTERNATIONAL CONFERENCE ON DIGITAL IMAGE COMPUTING: TECHNIQUES AND APPLICATIONS (DICTA 2021)
发表日期
2021
起止页码
598-605
DOI
10.1109/DICTA52665.2021.9647140
收录
ISTP

作者

  • X

    Xu, Sangni (通讯) (第一作者)

  • X

    Xiong, Hao

查看全部 4 位作者收起作者
  • W

    Wu, Qiuxia

  • W

    Wang, Zhiyong

登录解锁更多功能

  • 收藏这篇,随时在“我的 · 收藏”找回
  • 认领你的成果,生成推广素材
  • 关注作者获取最新成果
  • 加入项目组、协同写作
注册 / 登录

产品服务

  • 科研之友
  • 创新城
  • 科创云

服务支持

  • 帮助中心
  • 隐私政策
  • 服务条款

联系方式

在线客服:【】
客服热线:400-1616-289
电子邮箱:support@scholarmate.com

关注或下载科研之友

微信二维码
微信公众号
客户端下载二维码
下载客户端
科研成果科研人员科研机构科研动态爱瑞思软件

©2026 深圳市科研之友网络服务有限公司

公安备案图标粤公网安备 44030502000213
粤ICP备 16046710 号粤B2-20110417