Relative Camera Pose Estimation Using Convolutional Neural Networks

被引：119

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

页码：675 / 687

页数：13