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

Michael Boelstoft Holte

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

4 Citationer (Scopus)

Abstrakt

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

Fingeraftryk Dyk ned i forskningsemnerne om '3D Interest Point Detection using Local Surface Characteristics with Application in Action Recognition'. Sammen danner de et unikt fingeraftryk.

Citationsformater