A Novel 2.5D Feature Descriptor Compensating for Depth Rotation

Research output: Chapter in Book/Report/Conference proceedingArticle in proceedingsResearchpeer-review

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.
Original languageEnglish
Title of host publicationProceedings of the 12th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications
Volume4
PublisherSCITEPRESS Digital Library
Publication date2017
Pages158-166
ISBN (Electronic)978-989-758-225-7
DOIs
Publication statusPublished - 2017
Event12th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Porto, Portugal
Duration: 27. Feb 20171. Mar 2017
Conference number: 12

Conference

Conference12th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications
Number12
CountryPortugal
CityPorto
Period27/02/201701/03/2017

Keywords

  • Gabor filter
  • 2.5D
  • Depth rotation compensation
  • Descriptor

Fingerprint Dive into the research topics of 'A Novel 2.5D Feature Descriptor Compensating for Depth Rotation'. Together they form a unique fingerprint.

Cite this