loading
Papers Papers/2022 Papers Papers/2022

Research.Publish.Connect.

Paper

Paper Unlock
A Comparative Evaluation of 3D Keypoint Detectors in a RGB-D Object Dataset

Topics: Active and Robot Vision; Color and Texture Analyses; Features Extraction; Image Registration; Image-Based Modeling and 3D Reconstruction; Machine Learning Technologies for Vision; Segmentation and Grouping; Shape Representation and Matching; Stereo Vision and Structure from Motion; Vision for Robotics

Authors: Silvio Filipe and Luís A. Alexandre

Affiliation: IT - Instituto de Telecomunicações and University of Beira Interior, Portugal

Keyword(s): 3D Keypoints, 3D Interest Points, 3D Object Recognition, Performance Evaluation.

Related Ontology Subjects/Areas/Topics: Active and Robot Vision ; Applications ; Color and Texture Analyses ; Computer Vision, Visualization and Computer Graphics ; Features Extraction ; Geometry and Modeling ; Image and Video Analysis ; Image Registration ; Image-Based Modeling ; Motion, Tracking and Stereo Vision ; Pattern Recognition ; Robotics ; Segmentation and Grouping ; Shape Representation and Matching ; Software Engineering ; Stereo Vision and Structure from Motion

Abstract: When processing 3D point cloud data, features must be extracted from a small set of points, usually called keypoints. This is done to avoid the computational complexity required to extract features from all points in a point cloud. There are many keypoint detectors and this suggests the need of a comparative evaluation. When the keypoint detectors are applied to 3D objects, the aim is to detect a few salient structures which can be used, instead of the whole object, for applications like object registration, retrieval and data simplification. In this paper, we propose to do a description and evaluation of existing keypoint detectors in a public available point cloud library with real objects and perform a comparative evaluation on 3D point clouds. We evaluate the invariance of the 3D keypoint detectors according to rotations, scale changes and translations. The evaluation criteria used are the absolute and the relative repeatability rate. Using these criteria, we evaluate the robustn ess of the detectors with respect to changes of point-of-view. In our experiments, the method that achieved better repeatability rate was the ISS3D method. (More)

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 18.207.104.87

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:
Filipe, S. and A. Alexandre, L. (2014). A Comparative Evaluation of 3D Keypoint Detectors in a RGB-D Object Dataset. In Proceedings of the 9th International Conference on Computer Vision Theory and Applications (VISIGRAPP 2014) - Volume 2: VISAPP; ISBN 978-989-758-003-1; ISSN 2184-4321, SciTePress, pages 476-483. DOI: 10.5220/0004679904760483

@conference{visapp14,
author={Silvio Filipe. and Luís {A. Alexandre}.},
title={A Comparative Evaluation of 3D Keypoint Detectors in a RGB-D Object Dataset},
booktitle={Proceedings of the 9th International Conference on Computer Vision Theory and Applications (VISIGRAPP 2014) - Volume 2: VISAPP},
year={2014},
pages={476-483},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0004679904760483},
isbn={978-989-758-003-1},
issn={2184-4321},
}

TY - CONF

JO - Proceedings of the 9th International Conference on Computer Vision Theory and Applications (VISIGRAPP 2014) - Volume 2: VISAPP
TI - A Comparative Evaluation of 3D Keypoint Detectors in a RGB-D Object Dataset
SN - 978-989-758-003-1
IS - 2184-4321
AU - Filipe, S.
AU - A. Alexandre, L.
PY - 2014
SP - 476
EP - 483
DO - 10.5220/0004679904760483
PB - SciTePress