loading
Papers

Research.Publish.Connect.

Paper

Authors: Frederik Hagelskjær ; Norbert Krüger and Anders Glent Buch

Affiliation: University of Southern Denmark, Denmark

ISBN: 978-989-758-225-7

Keyword(s): Gabor Filter, Descriptor, Depth Rotation Compensation, 2.5D.

Related Ontology Subjects/Areas/Topics: Computer Vision, Visualization and Computer Graphics ; Early and Biologically-Inspired Vision ; Features Extraction ; Image and Video Analysis ; Image Formation and Preprocessing ; Image Generation Pipeline: Algorithms and Techniques

Abstract: We introduce a novel type of local image descriptor based on Gabor filter responses. Our method operates on RGB-D images. We use the depth information to compensate for perspective distortions caused by out-of-plane rotations. The descriptor contains the responses of a multi-resolution Gabor bank. Contrary to existing methods that rely on a dominant orientation estimate to achieve rotation invariance, we utilize the orientation information in the Gabor bank to achieve rotation invariance during the matching stage. Compared to SIFT and a recent also projective distortion compensating descriptor proposed for RGB-D data, our method achieves a significant increase in accuracy when tested on a wide-baseline RGB-D matching dataset.

PDF ImageFull Text

Download
CC BY-NC-ND 4.0

Sign In Guest: Register as new SciTePress user now for free.

Sign In SciTePress user: please login.

PDF ImageMy Papers

You are not signed in, therefore limits apply to your IP address 18.210.22.132

In the current month:
Recent papers: 100 available of 100 total
2+ years older papers: 200 available of 200 total

Paper citation in several formats:
Hagelskjær, F.; Krüger, N. and Buch, A. (2017). A Novel 2.5D Feature Descriptor Compensating for Depth Rotation.In Proceedings of the 12th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 4: VISAPP, (VISIGRAPP 2017) ISBN 978-989-758-225-7, pages 158-166. DOI: 10.5220/0006123201580166

@conference{visapp17,
author={Frederik Hagelskjær. and Norbert Krüger. and Anders Glent Buch.},
title={A Novel 2.5D Feature Descriptor Compensating for Depth Rotation},
booktitle={Proceedings of the 12th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 4: VISAPP, (VISIGRAPP 2017)},
year={2017},
pages={158-166},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0006123201580166},
isbn={978-989-758-225-7},
}

TY - CONF

JO - Proceedings of the 12th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 4: VISAPP, (VISIGRAPP 2017)
TI - A Novel 2.5D Feature Descriptor Compensating for Depth Rotation
SN - 978-989-758-225-7
AU - Hagelskjær, F.
AU - Krüger, N.
AU - Buch, A.
PY - 2017
SP - 158
EP - 166
DO - 10.5220/0006123201580166

Login or register to post comments.

Comments on this Paper: Be the first to review this paper.