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
  • [41] Self-supervised learning of LiDAR odometry based on spherical projection
    Fu, Xu
    Liu, Cong
    Zhang, Chengjin
    Sun, Zihao
    Song, Yong
    Xu, Qingyang
    Yuan, Xianfeng
    INTERNATIONAL JOURNAL OF ADVANCED ROBOTIC SYSTEMS, 2022, 19 (01):
  • [42] Geometric Consistency for Self-Supervised End-to-End Visual Odometry
    Iyer, Ganesh
    Murthy, J. Krishna
    Gupta, Gunshi
    Krishna, K. Madhava
    Paull, Liam
    PROCEEDINGS 2018 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION WORKSHOPS (CVPRW), 2018, : 380 - 388
  • [43] Self-Supervised Deep Visual Odometry Based on Geometric Attention Model
    Dai, Jiajia
    Gong, Xiaoxi
    Li, Yida
    Wang, Jun
    Wei, Mingqiang
    IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS, 2023, 24 (03) : 3157 - 3166
  • [44] Self-supervised Scale Recovery for Decoupled Visual-inertial Odometry
    Zhang, Tianyu
    Zhu, Dongchen
    Shi, Wenjun
    Liu, Yanqing
    Zhang, Guanghui
    Zhang, Xiaolin
    Li, Jiamao
    IEEE ROBOTICS AND AUTOMATION LETTERS, 2024, 9 (02) : 1612 - 1619
  • [45] Self-supervised Recurrent Visual Odometry, Depth Estimation, and Instance Segmentation
    Lin, Chujia
    Liu, Yiqi
    Chen, An
    Gao, Hongxia
    2024 5TH INTERNATIONAL CONFERENCE ON COMPUTING, NETWORKS AND INTERNET OF THINGS, CNIOT 2024, 2024, : 282 - 286
  • [46] SelfDeco: Self-Supervised Monocular Depth Completion in Challenging Indoor Environments
    Choi, Jaehoon
    Jung, Dongki
    Lee, Yonghan
    Kim, Deokhwa
    Manocha, Dinesh
    Lee, Donghwan
    2021 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION (ICRA 2021), 2021, : 467 - 474
  • [47] Simple contrastive learning in a self-supervised manner for robust visual question answering
    Yang, Shuwen
    Xiao, Luwei
    Wu, Xingjiao
    Xu, Junjie
    Wang, Linlin
    He, Liang
    COMPUTER VISION AND IMAGE UNDERSTANDING, 2024, 241
  • [48] ASCL: Adaptive self-supervised counterfactual learning for robust visual question answering
    Shu, Xinyao
    Yan, Shiyang
    Yang, Xu
    Wu, Ziheng
    Chen, Zhongfeng
    Lu, Zhenyu
    EXPERT SYSTEMS WITH APPLICATIONS, 2024, 248
  • [49] Absolute Monocular Depth Estimation on Robotic Visual and Kinematics Data via Self-Supervised Learning
    Wei, Ruofeng
    Li, Bin
    Zhong, Fangxun
    Mo, Hangjie
    Dou, Qi
    Liu, Yun-Hui
    Sun, Dong
    IEEE TRANSACTIONS ON AUTOMATION SCIENCE AND ENGINEERING, 2024, : 1 - 14
  • [50] Self-supervised learning for robust video indexing
    Ewerth, Ralph
    Freisleben, Bernd
    2006 IEEE INTERNATIONAL CONFERENCE ON MULTIMEDIA AND EXPO - ICME 2006, VOLS 1-5, PROCEEDINGS, 2006, : 1749 - +