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

Publikation: Bidrag til bog/antologi/rapport/konference proceedingKonferenceartikel i proceedingForskningpeer review

4 Citationer (Scopus)

Resumé

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.
OriginalsprogEngelsk
TitelIEEE International Conference on Image Processing
ForlagIEEE Signal Processing Society
Publikationsdato2014
Sider5736-5740
ISBN (Trykt)978-1-4799-5751-4
DOI
StatusUdgivet - 2014
BegivenhedIEEE International Conference on Image Processing (ICIP) - Paris, Frankrig
Varighed: 27 okt. 201430 okt. 2014

Konference

KonferenceIEEE International Conference on Image Processing (ICIP)
LandFrankrig
ByParis
Periode27/10/201430/10/2014

Fingerprint

Optical flows
Surface structure
Detectors
Experiments

Citer dette

Holte, M. B. (2014). 3D Interest Point Detection using Local Surface Characteristics with Application in Action Recognition. I IEEE International Conference on Image Processing (s. 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. s. 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. i IEEE International Conference on Image Processing. IEEE Signal Processing Society, s. 5736-5740, IEEE International Conference on Image Processing (ICIP), Paris, Frankrig, 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. s. 5736-5740.

Publikation: Bidrag til bog/antologi/rapport/konference proceedingKonferenceartikel i proceedingForskningpeer 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. I IEEE International Conference on Image Processing. IEEE Signal Processing Society. 2014. s. 5736-5740 https://doi.org/10.1109/ICIP.2014.7026160