Motion feature detection using steerable flow fields

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 i...

Full description

Saved in:
Bibliographic Details
Published inProceedings. 1998 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No.98CB36231) pp. 274 - 281
Main Authors Fleet, D.J., Black, M.J., Jepson, A.D.
Format Conference Proceeding
LanguageEnglish
Published IEEE 1998
Subjects
Bars
Cities and towns
Computer vision
Image motion analysis
Image sequence analysis
Layout
Motion detection
Motion estimation
Optical computing
Spatiotemporal phenomena
Online AccessGet full text

Cover

More Information
Summary: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.
ISBN:0818684976
9780818684975
ISSN:1063-6919
DOI:10.1109/CVPR.1998.698620