Degeneracy in Self-Calibration Revisited and a Deep Learning Solution for Uncalibrated SLAM

被引:0
作者
Zhuang, Bingbing [1 ]
Quoc-Huy Tran [2 ]
Lee, Gim Hee [1 ]
Cheong, Loong Fah [1 ]
Chandraker, Manmohan [3 ]
机构
[1] Natl Univ Singapore, Singapore, Singapore
[2] NEC Labs Amer Inc, Princeton, NJ USA
[3] Univ Calif San Diego, San Diego, CA 92103 USA
来源
2019 IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS (IROS) | 2019年
关键词
TRANSLATION; MODEL;
D O I
10.1109/iros40897.2019.8967912
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Self-calibration of camera intrinsics and radial distortion has a long history of research in the computer vision community. However, it remains rare to see real applications of such techniques to modern Simultaneous Localization And Mapping (SLAM) systems, especially in driving scenarios. In this paper, we revisit the geometric approach to this problem, and provide a theoretical proof that explicitly shows the ambiguity between radial distortion and scene depth when two-view geometry is used to self-calibrate the radial distortion. In view of such geometric degeneracy, we propose a learning approach that trains a convolutional neural network (CNN) on a large amount of synthetic data. We demonstrate the utility of our proposed method by applying it as a checkerboard-free calibration tool for SLAM, achieving comparable or superior performance to previous learning and hand-crafted methods.
引用
收藏
页码:3766 / 3773
页数:8
相关论文
共 46 条
  • [1] [Anonymous], 2012, CVPR
  • [2] Antunes M., 2017, P IEEE C COMP VIS PA, P4288
  • [3] DeepCalib: A Deep Learning Approach for Automatic Intrinsic Calibration of Wide Field-of-View Cameras
    Bogdan, Oleksandr
    Eckstein, Viktor
    Rameau, Francois
    Bazin, Jean-Charles
    [J]. PROCEEDINGS CVMP 2018: THE 15TH ACM SIGGRAPH EUROPEAN CONFERENCE ON VISUAL MEDIA PRODUCTION, 2018,
  • [4] Automatic Radial Distortion Estimation from a Single Image
    Bukhari, Faisal
    Dailey, Matthew N.
    [J]. JOURNAL OF MATHEMATICAL IMAGING AND VISION, 2013, 45 (01) : 31 - 45
  • [5] Byröd M, 2008, PROC CVPR IEEE, P2586
  • [6] Multitask learning
    Caruana, R
    [J]. MACHINE LEARNING, 1997, 28 (01) : 41 - 75
  • [7] A Continuous Occlusion Model for Road Scene Understanding
    Dhiman, Vikas
    Quoc-Huy Tran
    Corso, Jason J.
    Chandraker, Manmohan
    [J]. 2016 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2016, : 4331 - 4339
  • [8] Direct Sparse Odometry
    Engel, Jakob
    Koltun, Vladlen
    Cremers, Daniel
    [J]. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2018, 40 (03) : 611 - 625
  • [9] LSD-SLAM: Large-Scale Direct Monocular SLAM
    Engel, Jakob
    Schoeps, Thomas
    Cremers, Daniel
    [J]. COMPUTER VISION - ECCV 2014, PT II, 2014, 8690 : 834 - 849
  • [10] Fathy M. E., 2018, P EUR C COMP VIS, P803