DLR-Logo -> http://www.dlr.de
DLR Portal Home | Imprint | Privacy Policy | Contact | Deutsch
Fontsize: [-] Text [+]

Minimal Cases for Computing the Generalized Relative Pose Using Affine Correspondences

Guan, Banglei and Zhao, Ji and Barath, Daniel and Fraundorfer, Friedrich (2021) Minimal Cases for Computing the Generalized Relative Pose Using Affine Correspondences. IEEE International Conference on Computer Vision, 10. - 17. Oct. 2021, Canada. doi: 10.1109/ICCV48922.2021.00601.

[img] PDF

Official URL: https://ieeexplore.ieee.org/document/9710600


We propose three novel solvers for estimating the relative pose of a multi-camera system from affine correspondences (ACs). A new constraint is derived interpreting the relationship of ACs and the generalized camera model. Using the constraint, we demonstrate efficient solvers for two types of motions assumed. Considering that the cameras undergo planar motion, we propose a minimal solution using a single AC and a solver with two ACs to overcome the degenerate case. Also, we propose a minimal solution using two ACs with known vertical direction, e.g., from an IMU. Since the proposed methods require significantly fewer correspondences than state-of-the-art algorithms, they can be efficiently used within RANSAC for outlier removal and initial motion estimation. The solvers are tested both on synthetic data and on real-world scenes from the KITTI odometry benchmark. It is shown that the accuracy of the estimated poses is superior to the state-of-the-art techniques.

Item URL in elib:https://elib.dlr.de/146201/
Document Type:Conference or Workshop Item (Speech)
Title:Minimal Cases for Computing the Generalized Relative Pose Using Affine Correspondences
AuthorsInstitution or Email of AuthorsAuthor's ORCID iD
Guan, BangleiCollege of Aerospace Science and Engineering, Nat. University of Defense Technology, ChinaUNSPECIFIED
Zhao, JiTuSimple, zhaoji84 (at) gmail.comUNSPECIFIED
Barath, DanielETH ZürichUNSPECIFIED
Fraundorfer, Friedrichfriedrich.fraundorfer (at) dlr.deUNSPECIFIED
Refereed publication:Yes
Open Access:Yes
Gold Open Access:No
In ISI Web of Science:No
DOI :10.1109/ICCV48922.2021.00601
Page Range:pp. 1-10
Keywords:affine correspondences (ACs), KITTI odometry benchmark
Event Title:IEEE International Conference on Computer Vision
Event Location:Canada
Event Type:international Conference
Event Dates:10. - 17. Oct. 2021
HGF - Research field:Aeronautics, Space and Transport
HGF - Program:Transport
HGF - Program Themes:Road Transport
DLR - Research area:Transport
DLR - Program:V ST Straßenverkehr
DLR - Research theme (Project):V - NGC KoFiF
Location: Oberpfaffenhofen
Institutes and Institutions:Remote Sensing Technology Institute > Photogrammetry and Image Analysis
Deposited By: Knickl, Sabine
Deposited On:30 Nov 2021 14:21
Last Modified:20 Jul 2022 12:29

Repository Staff Only: item control page

Help & Contact
electronic library is running on EPrints 3.3.12
Copyright © 2008-2017 German Aerospace Center (DLR). All rights reserved.