Relative Camera Pose Estimation Using Convolutional Neural Networks

• Published in: Advanced Concepts for Intelligent Vision Systems Vol. 10617; pp. 675 - 687
• Main Authors: Melekhov, Iaroslav, Ylioinas, Juha, Kannala, Juho, Rahtu, Esa
• Format: Book Chapter
• Language: English
• Published: Switzerland Springer International Publishing AG 2017; Springer International Publishing
• Series: Lecture Notes in Computer Science
• Subjects: Deep neural networks; Relative camera pose estimation; Spatial pyramid pooling
• ISBN: 3319703528; 9783319703527
• ISSN: 0302-9743; 1611-3349
• DOI: 10.1007/978-3-319-70353-4_57

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.