Paper Info
Title
Recursive estimation of 3D motion and surface structure from local affine flow parameters.
Abstract
A recursive structure from motion algorithm based on optical flow measurements taken from an image sequence is described. It provides estimates of surface normals in addition to 3D motion and depth. The measurements are affine motion parameters which approximate the local flow fields associated with near-planar surface patches in the scene. These are integrated over time to give estimates of the 3D parameters using an extended Kalman filter. This also estimates the camera focal length and, so, the 3D estimates are metric. The use of parametric measurements means that the algorithm is computationally less demanding than previous optical flow approaches and the recursive filter builds in a degree of noise robustness. Results of experiments on synthetic and real image sequences demonstrate that the algorithm performs well.
Year
DOI
Venue
2005
10.1109/TPAMI.2005.83
IEEE Trans. Pattern Anal. Mach. Intell.
Keywords
Field
DocType
recursive filter,extended kalman filter,near-planar surface patch,previous optical flow approach,surface structure,affine motion parameter,image sequence,motion algorithm,recursive estimation,real image sequence,local affine flow parameters,local flow field,optical flow measurement,kalman filters,kalman filtering,optical flow,structure from motion,parameter estimation,optical filters,indexing terms,kalman filter,movement,layout,algorithms,feedback,artificial intelligence,motion estimation
Structure from motion,Affine transformation,Computer vision,Extended Kalman filter,Motion field,Computer science,Kalman filter,Artificial intelligence,Recursive filter,Motion estimation,Optical flow
Journal
Volume
Issue
ISSN
27
4
0162-8828
Citations 
PageRank 
References 
13
0.60
24
Authors
1
Name
Order
Citations
PageRank
Andrew Calway164554.66