Abstract | ||
---|---|---|
om This paper explores the direct motion estimation prob- lem assuming that video-rate depth information is avail- able, from either stereo cameras or other sensors. We use these depth measurements in the traditional linear bright- ness constraint equations, and we introduce a new depth constraint equation. As a result, estimation of certain types of motion, such as translation in depth and rotations out of the image plane, becomes more robust. We derive linear brightness and depth change constraint equations that gov- ern the velocity field in 3-D for both perspective and ortho- graphic camera projection models. These constraints are integrated jointly over image regions according to a rigid- body motion model, yielding a single linear system to ro- bustly track 3D object pose. Results are shown for tracking the pose of faces in sequences of synthetic and real images. For a color version of this paper and for video result se- quences, see http://www.interval.com/papers/1999-006. |
Year | DOI | Venue |
---|---|---|
1999 | 10.1109/ICCV.1999.791219 | ICCV |
Keywords | Field | DocType |
linear system,linear systems,brightness,motion estimation,tracking,rigid body motion,stereo vision,stereo cameras,shape,velocity field | Stereo cameras,Computer vision,Linear motion,Motion field,Orthographic projection,Linear system,Computer science,Image plane,Artificial intelligence,Real image,Motion estimation | Conference |
Volume | Issue | Citations |
1 | 1 | 40 |
PageRank | References | Authors |
3.45 | 12 | 5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Michael Harville | 1 | 369 | 35.55 |
Ali Rahimi | 2 | 1320 | 82.62 |
Trevor Darrell | 3 | 22413 | 1800.67 |
Gaile G. Gordon | 4 | 148 | 12.63 |
J. Woodfill | 5 | 1337 | 239.65 |