3D Interest Point Detection using Local Surface Characteristics with Application in Action Recognition

Research output: Contribution to book/anthology/report/conference proceedingArticle in proceedingResearchpeer-review

4 Citations (Scopus)

Abstract

In this paper we address the problem of detecting 3D inter- est points (IPs) using local surface characteristics. We con- tribute to this field by introducing a novel approach for detec- tion of 3D IPs directly on a surface mesh without any require- ments of additional image/video information. The proposed Difference-of-Normals (DoN) 3D IP detector operates on the surface mesh, and evaluates the surface structure (curvature) locally (per vertex) in the mesh data. We present an exam- ple of application in action recognition from a sequence of 3-dimensional geometrical data, where local 3D motion de- scriptors, Histogram of Optical 3D Flow (HOF3D), are ex- tracted from estimated 3D optical flow in the neighborhood of each IP and made view-invariant. Experiments on the pub- licly available i3DPost dataset show promising results.
Original languageEnglish
Title of host publicationIEEE International Conference on Image Processing
PublisherIEEE Signal Processing Society
Publication date2014
Pages5736-5740
ISBN (Print)978-1-4799-5751-4
DOIs
Publication statusPublished - 2014
EventIEEE International Conference on Image Processing (ICIP) - Paris, France
Duration: 27 Oct 201430 Oct 2014

Conference

ConferenceIEEE International Conference on Image Processing (ICIP)
CountryFrance
CityParis
Period27/10/201430/10/2014

Fingerprint

Optical flows
Surface structure
Detectors
Experiments

Cite this

Holte, M. B. (2014). 3D Interest Point Detection using Local Surface Characteristics with Application in Action Recognition. In IEEE International Conference on Image Processing (pp. 5736-5740). IEEE Signal Processing Society. https://doi.org/10.1109/ICIP.2014.7026160
Holte, Michael Boelstoft. / 3D Interest Point Detection using Local Surface Characteristics with Application in Action Recognition. IEEE International Conference on Image Processing. IEEE Signal Processing Society, 2014. pp. 5736-5740
@inproceedings{7b90f4aad71241958b26640068e1dae6,
title = "3D Interest Point Detection using Local Surface Characteristics with Application in Action Recognition",
abstract = "In this paper we address the problem of detecting 3D inter- est points (IPs) using local surface characteristics. We con- tribute to this field by introducing a novel approach for detec- tion of 3D IPs directly on a surface mesh without any require- ments of additional image/video information. The proposed Difference-of-Normals (DoN) 3D IP detector operates on the surface mesh, and evaluates the surface structure (curvature) locally (per vertex) in the mesh data. We present an exam- ple of application in action recognition from a sequence of 3-dimensional geometrical data, where local 3D motion de- scriptors, Histogram of Optical 3D Flow (HOF3D), are ex- tracted from estimated 3D optical flow in the neighborhood of each IP and made view-invariant. Experiments on the pub- licly available i3DPost dataset show promising results.",
author = "Holte, {Michael Boelstoft}",
year = "2014",
doi = "10.1109/ICIP.2014.7026160",
language = "English",
isbn = "978-1-4799-5751-4",
pages = "5736--5740",
booktitle = "IEEE International Conference on Image Processing",
publisher = "IEEE Signal Processing Society",
address = "United States",

}

Holte, MB 2014, 3D Interest Point Detection using Local Surface Characteristics with Application in Action Recognition. in IEEE International Conference on Image Processing. IEEE Signal Processing Society, pp. 5736-5740, IEEE International Conference on Image Processing (ICIP), Paris, France, 27/10/2014. https://doi.org/10.1109/ICIP.2014.7026160

3D Interest Point Detection using Local Surface Characteristics with Application in Action Recognition. / Holte, Michael Boelstoft.

IEEE International Conference on Image Processing. IEEE Signal Processing Society, 2014. p. 5736-5740.

Research output: Contribution to book/anthology/report/conference proceedingArticle in proceedingResearchpeer-review

TY - GEN

T1 - 3D Interest Point Detection using Local Surface Characteristics with Application in Action Recognition

AU - Holte, Michael Boelstoft

PY - 2014

Y1 - 2014

N2 - In this paper we address the problem of detecting 3D inter- est points (IPs) using local surface characteristics. We con- tribute to this field by introducing a novel approach for detec- tion of 3D IPs directly on a surface mesh without any require- ments of additional image/video information. The proposed Difference-of-Normals (DoN) 3D IP detector operates on the surface mesh, and evaluates the surface structure (curvature) locally (per vertex) in the mesh data. We present an exam- ple of application in action recognition from a sequence of 3-dimensional geometrical data, where local 3D motion de- scriptors, Histogram of Optical 3D Flow (HOF3D), are ex- tracted from estimated 3D optical flow in the neighborhood of each IP and made view-invariant. Experiments on the pub- licly available i3DPost dataset show promising results.

AB - In this paper we address the problem of detecting 3D inter- est points (IPs) using local surface characteristics. We con- tribute to this field by introducing a novel approach for detec- tion of 3D IPs directly on a surface mesh without any require- ments of additional image/video information. The proposed Difference-of-Normals (DoN) 3D IP detector operates on the surface mesh, and evaluates the surface structure (curvature) locally (per vertex) in the mesh data. We present an exam- ple of application in action recognition from a sequence of 3-dimensional geometrical data, where local 3D motion de- scriptors, Histogram of Optical 3D Flow (HOF3D), are ex- tracted from estimated 3D optical flow in the neighborhood of each IP and made view-invariant. Experiments on the pub- licly available i3DPost dataset show promising results.

U2 - 10.1109/ICIP.2014.7026160

DO - 10.1109/ICIP.2014.7026160

M3 - Article in proceeding

SN - 978-1-4799-5751-4

SP - 5736

EP - 5740

BT - IEEE International Conference on Image Processing

PB - IEEE Signal Processing Society

ER -

Holte MB. 3D Interest Point Detection using Local Surface Characteristics with Application in Action Recognition. In IEEE International Conference on Image Processing. IEEE Signal Processing Society. 2014. p. 5736-5740 https://doi.org/10.1109/ICIP.2014.7026160