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 3-D 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 3-D parameters using an extended Kalman filter. This also estimates the camera focal length and hence the 3-D 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.
|Translated title of the contribution||Recursive Estimation of 3-D Motion and Surface Structure from Local Affine Flow Parameters|
|Pages (from-to)||562 - 574|
|Number of pages||13|
|Journal||IEEE Transactions on Pattern Analysis and Machine Intelligence|
|Publication status||Published - Apr 2005|
Bibliographical notePublisher: Institute of Electrical and Electronic Engineers