Actions

Download Analytics Citations

Export to: EndNote  |  Zotero  |  Mendeley

Collections

This file is not currently in any collections.

On Depth Error from Spherical Camera Calibration within Omnidirectional Stereo Vision [dataset] Open Access

As a depth sensing approach, whilst stereo vision provides a good compromise between accuracy and cost, a key limitation is the limited field of view of the conventional cameras that are used within most stereo configurations. By contrast, the use of spherical cameras within a stereo configuration offers omnidirectional stereo sensing. However, despite the presence of significant image distortion in spherical camera images, only very limited attempts have been made to study and quantify omnidirectional stereo depth accuracy. In this paper we construct such an omnidirectional stereo system that is capable of real-time 360 degree disparity map reconstruction as the basis for such a study. We first investigate the accuracy of using a standard spherical camera model for calibration combined with a longitude-latitude projection for omnidirectional stereo, and show that the depth error increases significantly as the angle from the camera optical axis approaches the limits of the camera field of view. In contrast, we then consider an alternative calibration approach via the use of perspective undistortion with a conventional pinhole camera model allowing omnidirectional cameras to be mapped to a conventional rectilinear stereo formulation. We find that conversely this proposed approach exhibits improved depth accuracy at large angles from the camera optical axis when compared to omnidirectional stereo depth based on a spherical camera model calibration. [ On Depth Error from Spherical Camera Calibration within Omnidirectional Stereo Vision (M. Groom, T.P. Breckon), In Proc. Int. Conf. on Pattern Recognition, IEEE, 2022. ] Supporting dataset - all stereo camera calibration and depth evaluation images used in this study.

Descriptions

Resource type

Dataset

Contributors

Creator: Groom, Michael ¹
Editor: Breckon, Toby ¹

¹ Durham University, UK

Funder

Durham University, UK

Research methods

Numerical methods in computational and multiple view geometry.

Other description

Predominantly image files in PNG format.

Keyword

Stereo vision
Spherical camera
Angular disparity
Stereo calibration
Computer vision
3D vision

Subject

Engineering
Computer science
Stereoscopic views
Cameras

Location

Durham, England, United Kingdom

Language

English

Cited in

doi:10.1109/ICPR56361.2022.9956197

Identifier

ark:/32150/r13197xm075
doi:10.15128/r13197xm075

Rights

Creative Commons Attribution 4.0 International (CC BY)

Publisher

Durham University

Date Created

March 2021

File Details

Depositor

T. Breckon

Date Uploaded

6 June 2022, 11:06:59

Date Modified

10 January 2023, 14:01:38

Audit Status

Audits have not yet been run on this file.

Characterization

File format: zip (ZIP Format)

Mime type: application/zip

File size: 352150738

Last modified: 2022:06:12 23:36:57+01:00

Filename: groom-icpr-2022_v2.zip

Original checksum: d0418b7a9285843d74214bc13282aeab