Camera Relocalization by Computing Pairwise Relative Poses Using Convolutional Neural Network

Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

Abstract

We propose a new deep learning based approach for camera relocalization. Our approach localizes a given query image by using a convolutional neural network (CNN) for first retrieving similar database images and then predicting the relative pose between the query and the database images, whose poses are known. The camera location for the query image is obtained via triangulation from two relative translation estimates using a RANSAC based approach. Each relative pose estimate provides a hypothesis for the camera orientation and they are fused in a second RANSAC scheme. The neural network is trained for relative pose estimation in an end-to-end manner using training image pairs. In contrast to previous work, our approach does not require scene-specific training of the network, which improves scalability, and it can also be applied to scenes which are not available during the training of the network. As another main contribution, we release a challenging indoor localisation dataset covering 5 different scenes registered to a common coordinate frame. We evaluate our approach using both our own dataset and the standard 7 Scenes benchmark. The results show that the proposed approach generalizes
well to previously unseen scenes and compares favourably to other recent CNN-based
methods
Original languageEnglish
Title of host publication2017 IEEE International Conference on Computer Vision Workshops (ICCVW)
PublisherIEEE
Pages920-929
ISBN (Electronic)978-1-5386-1034-3
ISBN (Print)978-1-5386-1035-0
DOIs
Publication statusPublished - 2017
MoE publication typeA4 Article in a conference publication
EventIEEE International Conference on Computer Vision Workshops - Venice, Italy
Duration: 22 Oct 201729 Oct 2017
Conference number: ICCVW

Publication series

NameIEEE International Conference on Computer Vision Workshops (ICCVW)
PublisherIEEE
ISSN (Electronic)2473-9944

Workshop

WorkshopIEEE International Conference on Computer Vision Workshops
CountryItaly
CityVenice
Period22/10/201729/10/2017

Fingerprint Dive into the research topics of 'Camera Relocalization by Computing Pairwise Relative Poses Using Convolutional Neural Network'. Together they form a unique fingerprint.

  • Equipment

    Science-IT

    Mikko Hakala (Manager)

    School of Science

    Facility/equipment: Facility

  • Cite this

    Laskar, Z., Melekhov, I., Kalia, S., & Kannala, J. (2017). Camera Relocalization by Computing Pairwise Relative Poses Using Convolutional Neural Network. In 2017 IEEE International Conference on Computer Vision Workshops (ICCVW) (pp. 920-929). (IEEE International Conference on Computer Vision Workshops (ICCVW) ). IEEE. https://doi.org/10.1109/ICCVW.2017.113