Driven to Distraction: Self-Supervised Distractor Learning for Robust Monocular Visual Odometry in Urban Environments

被引:0
|
作者
Barnes, Dan [1 ]
Maddern, Will [1 ]
Pascoe, Geoffrey [1 ]
Posner, Ingmar [1 ]
机构
[1] Univ Oxford, Dept Engn Sci, Oxford Robot Inst, Oxford, England
基金
英国工程与自然科学研究理事会;
关键词
D O I
暂无
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
We present a self-supervised approach to ignoring "distractors" in camera images for the purposes of robustly estimating vehicle motion in cluttered urban environments. We leverage offline multi-session mapping approaches to automatically generate a per-pixel ephemerality mask and depth map for each input image, which we use to train a deep convolutional network. At run-time we use the predicted ephemerality and depth as an input to a monocular visual odometry (VO) pipeline, using either sparse features or dense photometric matching. Our approach yields metric-scale VO using only a single camera and can recover the correct egomotion even when 90% of the image is obscured by dynamic, independently moving objects. We evaluate our robust VO methods on more than 400km of driving from the Oxford RobotCar Dataset and demonstrate reduced odometry drift and significantly improved egomotion estimation in the presence of large moving vehicles in urban traffic.
引用
收藏
页码:1894 / 1900
页数:7
相关论文
共 50 条
  • [21] Scale-Aware Visual-Inertial Depth Estimation and Odometry Using Monocular Self-Supervised Learning
    Lee, Chungkeun
    Kim, Changhyeon
    Kim, Pyojin
    Lee, Hyeonbeom
    Kim, H. Jin
    IEEE ACCESS, 2023, 11 : 24087 - 24102
  • [22] Fine-MVO: Toward Fine-Grained Feature Enhancement for Self-Supervised Monocular Visual Odometry in Dynamic Environments
    Wei, Wenhui
    Ping, Yang
    Li, Jiadong
    Liu, Xin
    Zhou, Yangfan
    IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS, 2024, 25 (10) : 13947 - 13960
  • [23] Hybrid self-supervised monocular visual odometry system based on spatio-temporal features
    Yuan, Shuangjie
    Zhang, Jun
    Lin, Yujia
    Yang, Lu
    ELECTRONIC RESEARCH ARCHIVE, 2024, 32 (05): : 3543 - 3568
  • [24] DeepVIO: Self-supervised Deep Learning of Monocular Visual Inertial Odometry using 3D Geometric Constraints
    Han, Liming
    Lin, Yimin
    Du, Guoguang
    Lian, Shiguo
    2019 IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS (IROS), 2019, : 6906 - 6913
  • [25] Self-Supervised Deep Visual Odometry with Online Adaptation
    Li, Shunkai
    Wang, Xin
    Cao, Yingdian
    Xue, Fei
    Yan, Zike
    Zha, Hongbin
    2020 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2020, : 6338 - 6347
  • [26] Self-supervised Visual Odometry Based on Geometric Consistency
    Song, Rujun
    Liu, Jiaqi
    Liao, Kaisheng
    Xiao, Zhuoling
    Yan, Bo
    2023 IEEE INTERNATIONAL SYMPOSIUM ON CIRCUITS AND SYSTEMS, ISCAS, 2023,
  • [27] Robust Visual Odometry for Complex Urban Environments
    Parra, Ignacio
    Angel Sotelo, Miguel
    Vlacic, Ljubo
    2008 IEEE INTELLIGENT VEHICLES SYMPOSIUM, VOLS 1-3, 2008, : 916 - +
  • [28] Monocular Visual Odometry in Urban Environments Using an Omnidirectional Camera
    Tardif, Jean-Philippe
    Pavlidis, Yanis
    Daniilidis, Kostas
    2008 IEEE/RSJ INTERNATIONAL CONFERENCE ON ROBOTS AND INTELLIGENT SYSTEMS, VOLS 1-3, CONFERENCE PROCEEDINGS, 2008, : 2531 - 2538
  • [29] Self-supervised Learning of LiDAR Odometry for Robotic Applications
    Nubert, Julian
    Khattak, Shehryar
    Hutter, Marco
    2021 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION (ICRA 2021), 2021, : 9601 - 9607
  • [30] MaskVO: Self-Supervised Visual Odometry with a Learnable Dynamic Mask
    Xuan, Weihao
    Ren, Ruijie
    Wu, Siyuan
    Chen, Changhao
    2022 IEEE/SICE INTERNATIONAL SYMPOSIUM ON SYSTEM INTEGRATION (SII 2022), 2022, : 225 - 231