Relative Camera Pose Estimation Using Convolutional Neural Networks

被引:102
|
作者
Melekhov, Iaroslav [1 ]
Ylioinas, Juha [1 ]
Kannala, Juho [1 ]
Rahtu, Esa [2 ]
机构
[1] Aalto Univ, Helsinki, Finland
[2] Tampere Univ Technol, Tampere, Finland
来源
ADVANCED CONCEPTS FOR INTELLIGENT VISION SYSTEMS (ACIVS 2017) | 2017年 / 10617卷
关键词
Relative camera pose estimation; Deep neural networks; Spatial pyramid pooling;
D O I
10.1007/978-3-319-70353-4_57
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
This paper presents a convolutional neural network based approach for estimating the relative pose between two cameras. The proposed network takes RGB images from both cameras as input and directly produces the relative rotation and translation as output. The system is trained in an end-to-end manner utilising transfer learning from a large scale classification dataset. The introduced approach is compared with widely used local feature based methods (SURF, ORB) and the results indicate a clear improvement over the baseline. In addition, a variant of the proposed architecture containing a spatial pyramid pooling (SPP) layer is evaluated and shown to further improve the performance.
引用
收藏
页码:675 / 687
页数:13
相关论文
共 50 条
  • [21] Visual Camera Re-Localization Using Graph Neural Networks and Relative Pose Supervision
    Turkoglu, Mehmet Ozgur
    Brachmann, Eric
    Schindler, Konrad
    Brostow, Gabriel J.
    Monszpart, Aron
    2021 INTERNATIONAL CONFERENCE ON 3D VISION (3DV 2021), 2021, : 145 - 155
  • [22] Choreographic Pose Identification using Convolutional Neural Networks
    Bakalos, Nikolaos
    Rallis, Ioannis
    Doulamis, Nikolaos
    Doulamis, Anastasios
    Protopapadakis, Eftychios
    Voulodimos, Athanasios
    2019 11TH INTERNATIONAL CONFERENCE ON VIRTUAL WORLDS AND GAMES FOR SERIOUS APPLICATIONS (VS-GAMES), 2019, : 95 - 101
  • [23] Domain adaptation of networks for camera pose estimation: Learning camera pose estimation without pose labels
    Langerman, Jack
    Qiu, Ziming
    Sörös, Gábor
    Sebok, Dávid
    Wang, Yao
    Huang, Howard
    arXiv, 2021,
  • [24] Deep Convolutional Neural Networks for Efficient Pose Estimation in Gesture Videos
    Pfister, Tomas
    Simonyan, Karen
    Charles, James
    Zisserman, Andrew
    COMPUTER VISION - ACCV 2014, PT I, 2015, 9003 : 538 - 552
  • [25] Real-time Human Pose Estimation with Convolutional Neural Networks
    Linna, Marko
    Kannala, Juho
    Rahtu, Esa
    PROCEEDINGS OF THE 13TH INTERNATIONAL JOINT CONFERENCE ON COMPUTER VISION, IMAGING AND COMPUTER GRAPHICS THEORY AND APPLICATIONS (VISIGRAPP 2018), VOL 5: VISAPP, 2018, : 335 - 342
  • [26] Real-time human pose estimation on a smart walker using convolutional neural networks
    Palermo, Manuel
    Moccia, Sara
    Migliorelli, Lucia
    Frontoni, Emanuele
    Santos, Cristina P.
    EXPERT SYSTEMS WITH APPLICATIONS, 2021, 184
  • [27] 3D Human Pose Estimation Using Convolutional Neural Networks with 2D Pose Information
    Park, Sungheon
    Hwang, Jihye
    Kwak, Nojun
    COMPUTER VISION - ECCV 2016 WORKSHOPS, PT III, 2016, 9915 : 156 - 169
  • [28] Camera Model Identification Using Convolutional Neural Networks
    Kuzin, Artur
    Fattakhov, Artur
    Kibardin, Ilya
    Iglovikov, Vladimir I.
    Dautov, Ruslan
    2018 IEEE INTERNATIONAL CONFERENCE ON BIG DATA (BIG DATA), 2018, : 3107 - 3110
  • [29] Multispectral Camera Calibration Using Convolutional Neural Networks
    Trujillo, Ivan A. Juarez
    de Paz, Jonny P. Zavala
    Sandoval, Omar Palillero
    Velasquez, Francisco A. Castillo
    COMPUTACION Y SISTEMAS, 2023, 27 (03): : 801 - 810
  • [30] Gaze estimation using convolutional neural networks
    Karmi, Rawdha
    Rahmany, Ines
    Khlifa, Nawres
    SIGNAL IMAGE AND VIDEO PROCESSING, 2024, 18 (01) : 389 - 398