Relative Camera Pose Estimation Using Convolutional Neural Networks

Abstract

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.

To be published in proceedings of Advanced Concepts for Intelligent Vision Systems (ACIVS) 2017

References in corpus (2)

• DeMoN: Depth and Motion Network for Learning Monocular Stereo
• DeepVO: A Deep Learning approach for Monocular Visual Odometry

Cited by in corpus (5)

• RegNet: Learning the Optimization of Direct Image-to-Image Pose Registration
• Siamese Convolutional Neural Network for Sub-millimeter-accurate Camera Pose Estimation and Visual Servoing
• SymmNet: A Symmetric Convolutional Neural Network for Occlusion Detection
• Drone Path-Following in GPS-Denied Environments using Convolutional Networks
• Associative3D: Volumetric Reconstruction from Sparse Views