Visual-Inertial 2D Feature Tracking based on an Affine Photometric Model

Hdl Handle:
http://hdl.handle.net/10034/620235
Title:
Visual-Inertial 2D Feature Tracking based on an Affine Photometric Model
Authors:
Aufderheide, Dominik; Edwards, Gerard; Krybus, Werner
Abstract:
The robust tracking of point features throughout an image sequence is one fundamental stage in many different computer vision algorithms (e.g. visual modelling, object tracking, etc.). In most cases, this tracking is realised by means of a feature detection step and then a subsequent re-identification of the same feature point, based on some variant of a template matching algorithm. Without any auxiliary knowledge about the movement of the camera, actual tracking techniques are only robust for relatively moderate frame-to-frame feature displacements. This paper presents a framework for a visual-inertial feature tracking scheme, where images and measurements of an inertial measurement unit (IMU) are fused in order to allow a wider range of camera movements. The inertial measurements are used to estimate the visual appearance of a feature’s local neighbourhood based on a affine photometric warping model.
Affiliation:
South Westphalia University of Applied Sciences, University of Chester, South Westphalia University of Applied Sciences
Citation:
Aufderheide, D., Edwards, G., & Krybus, W. (2015). Visual-inertial 2D feature tracking based on an affine photometric model. In J. M. R. S. Tavares & R. N. Jorge (eds.) Developments in medical image processing and computational vision, volume 19 of the series lecture notes in computational vision and biomechanics (pp. 297-317). Switzerland: Springer International Publishing.
Publisher:
Springer
Publication Date:
2015
URI:
http://hdl.handle.net/10034/620235
DOI:
10.1007/978-3-319-13407-9_18
Additional Links:
http://link.springer.com/chapter/10.1007/978-3-319-13407-9_18
Type:
Book chapter
Language:
en
ISBN:
9783319134062; 9783319134079
Appears in Collections:
Electronic and Electrical Engineering

Full metadata record

DC FieldValue Language
dc.contributor.authorAufderheide, Dominiken
dc.contributor.authorEdwards, Gerarden
dc.contributor.authorKrybus, Werneren
dc.date.accessioned2016-11-01T10:02:39Z-
dc.date.available2016-11-01T10:02:39Z-
dc.date.issued2015-
dc.identifier.citationAufderheide, D., Edwards, G., & Krybus, W. (2015). Visual-inertial 2D feature tracking based on an affine photometric model. In J. M. R. S. Tavares & R. N. Jorge (eds.) Developments in medical image processing and computational vision, volume 19 of the series lecture notes in computational vision and biomechanics (pp. 297-317). Switzerland: Springer International Publishing.en
dc.identifier.isbn9783319134062en
dc.identifier.isbn9783319134079en
dc.identifier.doi10.1007/978-3-319-13407-9_18-
dc.identifier.urihttp://hdl.handle.net/10034/620235-
dc.description.abstractThe robust tracking of point features throughout an image sequence is one fundamental stage in many different computer vision algorithms (e.g. visual modelling, object tracking, etc.). In most cases, this tracking is realised by means of a feature detection step and then a subsequent re-identification of the same feature point, based on some variant of a template matching algorithm. Without any auxiliary knowledge about the movement of the camera, actual tracking techniques are only robust for relatively moderate frame-to-frame feature displacements. This paper presents a framework for a visual-inertial feature tracking scheme, where images and measurements of an inertial measurement unit (IMU) are fused in order to allow a wider range of camera movements. The inertial measurements are used to estimate the visual appearance of a feature’s local neighbourhood based on a affine photometric warping model.en
dc.language.isoenen
dc.publisherSpringeren
dc.relation.urlhttp://link.springer.com/chapter/10.1007/978-3-319-13407-9_18en
dc.rights.urihttp://creativecommons.org/licenses/by-nc-nd/4.0/*
dc.subjectComputer Visionen
dc.subjectFeature Detectionen
dc.subjectData Fusionen
dc.subjectInertial Measurementsen
dc.subjectAffine photometric warping modelen
dc.titleVisual-Inertial 2D Feature Tracking based on an Affine Photometric Modelen
dc.typeBook chapteren
dc.contributor.departmentSouth Westphalia University of Applied Sciences, University of Chester, South Westphalia University of Applied Sciencesen
dc.date.accepted2015-04-08-
or.grant.openaccessYesen
rioxxterms.funderUnfundeden
rioxxterms.identifier.projectUnfundeden
rioxxterms.versionAMen
rioxxterms.licenseref.startdate2215-12-31en
This item is licensed under a Creative Commons License
Creative Commons
All Items in ChesterRep are protected by copyright, with all rights reserved, unless otherwise indicated.