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
  • [31] Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization
    Selvaraju, Ramprasaath R.
    Cogswell, Michael
    Das, Abhishek
    Vedantam, Ramakrishna
    Parikh, Devi
    Batra, Dhruv
    [J]. 2017 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV), 2017, : 618 - 626
  • [32] Srivastava S., 2019, P IEEE RSJ INT C INT
  • [33] Estimating the fundamental matrix under pure translation and radial distortion
    Steger, Carsten
    [J]. ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING, 2012, 74 : 202 - 217
  • [34] Sturm P., 2001, P 2001 IEEE COMPUTER, V2, pII
  • [35] Tran Q. H., 2014, THESIS
  • [36] A new calibration model of camera lens distortion
    Wang, Jianhua
    Shi, Fanhuai
    Zhang, Jing
    Liu, Yuncai
    [J]. PATTERN RECOGNITION, 2008, 41 (02) : 607 - 615
  • [37] Wang Z, 2019, IEEE CONF COMPU INTE
  • [38] Wildenauer H., CLOSED FORM SOLUTION
  • [39] Critical Configurations For Radial Distortion Self-Calibration
    Wu, Changchang
    [J]. 2014 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2014, : 25 - 32
  • [40] Challenges in Monocular Visual Odometry: Photometric Calibration, Motion Bias, and Rolling Shutter Effect
    Yang, Nan
    Wang, Rui
    Gao, Xiang
    Cremers, Daniel
    [J]. IEEE ROBOTICS AND AUTOMATION LETTERS, 2018, 3 (04): : 2878 - 2885