Resumé
| Originalsprog | Engelsk |
|---|---|
| Titel | IEEE International Conference on Image Processing |
| Forlag | IEEE Signal Processing Society |
| Publikationsdato | 2014 |
| Sider | 5736-5740 |
| ISBN (Trykt) | 978-1-4799-5751-4 |
| DOI | |
| Status | Udgivet - 2014 |
| Begivenhed | IEEE International Conference on Image Processing (ICIP) - Paris, Frankrig Varighed: 27 okt. 2014 → 30 okt. 2014 |
Konference
| Konference | IEEE International Conference on Image Processing (ICIP) |
|---|---|
| Land | Frankrig |
| By | Paris |
| Periode | 27/10/2014 → 30/10/2014 |
Fingerprint
Citer dette
}
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 proceeding › Konferenceartikel i proceeding › Forskning › peer 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 -