Name
Abstract | ||
|---|---|---|
In this paper we propose a new 3D kernel for the recovery of 3D-orientation signatures. The kernel is a Gaussian function defined in local spherical coordinates and its Cartesian support has the shape of a truncated cone with its axis in the radial direction and very small angular support. A set of such kernels is obtained by uniformly sampling the 2D space of polar and azimuth angles. The projection of a local neighborhood on such a kernel set produces a local 3D-orientation signature. In the case of spatiotemporal analysis, such a kernel set can be applied either on the derivative space of a local neighborhood or on the local Fourier transform. The well known planes arising from single or multiple motion produce maxima in the orientation signature. Due to the kernel's local support spatiotemporal signatures possess higher orientation resolution than 3D steerable filters and motion maxima can be detected and localized more accurately. We describe and show in experiments the superiority of the proposed kernels compared to Hough transformation or EM-based multiple motion detection. |
Year | DOI | Venue |
|---|---|---|
2001 | 10.1109/CVPR.2001.990490 | CVPR (1) |
Keywords | Field | DocType |
fourier transforms,azimuth angles,cartesian support,derivative space,conic kernel filtering,angular support,local fourier transform,spatiotemporal signatures,polar angles,gaussian function,3d kernel,spatiotemporal analysis,motion estimation,multiple motion analysis,3d orientation signature recovery,motion maxima,2d space sampling,computer vision,local spherical coordinates,local neighborhood projection,truncated cone,stereo image processing,azimuth,sampling methods,kernel,filtering,shape,fourier transform | Kernel (linear algebra),Computer vision,Motion field,Motion detection,Computer science,Hough transform,Fourier transform,Artificial intelligence,Motion estimation,Spherical coordinate system,Gaussian function | Conference |
Volume | ISSN | ISBN |
1 | 1063-6919 | 0-7695-1272-0 |
Citations | PageRank | References |
2 | 0.40 | 19 |
Authors | ||
3 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Weichuan Yu | 1 | 943 | 57.38 |
| Gerald Sommer | 2 | 269 | 21.93 |
| Konstantinos Daniilidis | 3 | 3122 | 255.45 |