Image deformations are better than optical flow

Authors:
C. Tomasi;J. Shi
Affiliations:
Computer Science Department, Stanford University Stanford, CA 94305, U.S.A.;Computer Science Division, University of California at Berkeley Berkeley, CA 94720, U.S.A.
Venue:
Mathematical and Computer Modelling: An International Journal
Year:
1996

Citing 5
Cited 0

Facts on optic flow

Biological Cybernetics
Motion and Structure From Two Perspective Views: Algorithms, Error Analysis, and Error Estimation

IEEE Transactions on Pattern Analysis and Machine Intelligence
Subspace methods for recovering rigid motion I: algorithm and implementation

International Journal of Computer Vision
Determining Three-Dimensional Motion and Structure from Optical Flow Generated by Several Moving Objects

IEEE Transactions on Pattern Analysis and Machine Intelligence
Uniqueness and Estimation of Three-Dimensional Motion Parameters of Rigid Objects with Curved Surfaces

IEEE Transactions on Pattern Analysis and Machine Intelligence

Quantified Score

Hi-index	0.98

Visualization

Abstract

In many computer vision applications it is necessary to compute the direction of heading of a moving camera from the images it produces. Traditionally, this computation has been based on the optical flow, that is, on the motion of point features in the field of view. We show that the differential changes in the angles between the projection rays of pairs of point features are a better input for this purpose. These angles, the image deformations, do not depend on viewer rotation, so the key problem of separating the effects of rotation from those of translation is solved at the input. Experiments show both the feasibility of the method on real images and the advantages of using deformations rather than optical flow.