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
  • [41] Real-Time Landing Spot Detection and Pose Estimation on Thermal Images Using Convolutional Neural Networks
    Chen, Xudong
    Lin, Feng
    Hamid, Mohamed Redhwan Abdul
    Teo, Swee Huat
    Phang, Swee King
    2018 IEEE 14TH INTERNATIONAL CONFERENCE ON CONTROL AND AUTOMATION (ICCA), 2018, : 998 - 1003
  • [42] Relative Camera Pose Estimation using Synthetic Data with Domain Adaptation via Cycle-Consistent Adversarial Networks
    Chenhao Yang
    Yuyi Liu
    Andreas Zell
    Journal of Intelligent & Robotic Systems, 2021, 102
  • [43] Relative Camera Pose Estimation using Synthetic Data with Domain Adaptation via Cycle-Consistent Adversarial Networks
    Yang, Chenhao
    Liu, Yuyi
    Zell, Andreas
    JOURNAL OF INTELLIGENT & ROBOTIC SYSTEMS, 2021, 102 (04)
  • [44] Object Detection and Pose Estimation based on Convolutional Neural Networks Trained with Synthetic Data
    Josifovski, Josip
    Kerzel, Matthias
    Pregizer, Christoph
    Posniak, Lukas
    Wermter, Stefan
    2018 IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS (IROS), 2018, : 6269 - 6276
  • [45] Sparse Representation and Convolutional Neural Networks for 3D Human Pose Estimation
    Alikarami, Hassan
    Yaghmaee, Farzin
    Fadaeieslam, Mohammad Javad
    2017 3RD IRANIAN CONFERENCE ON SIGNAL PROCESSING AND INTELLIGENT SYSTEMS (ICSPIS), 2017, : 188 - 192
  • [46] Concept Detection and Face Pose Estimation Using Lightweight Convolutional Neural Networks for Steering Drone Video Shooting
    Passalis, Nikolaos
    Tefas, Anastasios
    2017 25TH EUROPEAN SIGNAL PROCESSING CONFERENCE (EUSIPCO), 2017, : 71 - 75
  • [47] On the use of Convolutional Neural Networks for Graphical Model-based Human Pose Estimation
    Huynh Vu
    Cheng, Eva
    Wilkinson, Richardt
    Lech, Margaret
    2017 INTERNATIONAL CONFERENCE ON RECENT ADVANCES IN SIGNAL PROCESSING, TELECOMMUNICATIONS & COMPUTING (SIGTELCOM), 2017, : 88 - 93
  • [48] Head Pose Estimation in the Wild Assisted by Facial Landmarks Based on Convolutional Neural Networks
    Xia, Jiahao
    Cao, Libo
    Zhang, Guanjun
    Liao, Jiacai
    IEEE ACCESS, 2019, 7 : 48470 - 48483
  • [49] Vegetation Cover Estimation Using Convolutional Neural Networks
    Ghazal, Mohammed Asaad
    Mahmoud, Ali
    Aslantas, Ali
    Soliman, Ahmed
    Shalaby, Ahmed
    Benediktsson, Jon Atli
    El-Baz, Ayman
    IEEE ACCESS, 2019, 7 : 132563 - 132576
  • [50] Epicentral Region Estimation Using Convolutional Neural Networks
    Cruz, Leonel
    Tous, Ruben
    Otero, Beatriz
    Alvarado, Leonardo
    Mus, Sergi
    Rojas, Otilio
    MACHINE LEARNING, OPTIMIZATION, AND DATA SCIENCE (LOD 2021), PT I, 2022, 13163 : 541 - 552