Name
Abstract | ||
|---|---|---|
The estimation and detection of occlusion boundaries and moving bars are important and challenging problems in image sequence analysis. Here, we model such motion features as linear combinations of steerable basis flow fields. These models constrain the interpretation of image motion, and are used in the same way as translational or affine motion models. We estimate the subspace coefficients of the motion feature models directly from spatiotemporal image derivatives using a robust regression method. From the subspace coefficients we detect the presence of a motion feature and solve for the orientation of the feature and the relative velocities of the surfaces. Our method does not require the prior computation of optical flow and recovers accurate estimates of orientation and velocity. |
Year | DOI | Venue |
|---|---|---|
1998 | 10.1109/CVPR.1998.698620 | Santa Barbara, CA |
Keywords | Field | DocType |
feature extraction,image sequences,motion estimation,affine motion models,image motion,image sequence analysis,motion feature detection,occlusion boundaries detection,optical flow,orientation,robust regression method,spatiotemporal image derivatives,steerable flow fields,subspace coefficients | Computer vision,Linear motion,Motion field,Image derivatives,Pattern recognition,Motion detection,Subspace topology,Computer science,Feature extraction,Artificial intelligence,Motion estimation,Optical flow | Conference |
Volume | Issue | ISSN |
1998 | 1 | 1063-6919 |
ISBN | Citations | PageRank |
0-8186-8497-6 | 13 | 2.03 |
References | Authors | |
11 | 3 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| David J. Fleet | 1 | 5236 | 550.74 |
| Michael J. Black | 2 | 11233 | 1536.41 |
| Jepson, A.D. | 3 | 402 | 81.91 |