A Comment on "Analysis of Video Image Sequences Using Point and Line Correspondences"
This work addresses a theoretical debate in computer vision about motion parameter estimation, but it is incremental as it clarifies prior claims without introducing new methods.
The authors refute two claims by Wang et al., arguing that lines do not aid motion parameter recognition from two images and that four points are insufficient for recovery under perspective projection; they show that four points suffice under orthogonal projection and five points simplify the solution to a linear system.
In this paper we would like to deny the results of Wang et al. raising two fundamental claims: * A line does not contribute anything to recognition of motion parameters from two images * Four traceable points are not sufficient to recover motion parameters from two perspective To be constructive, however, we show that four traceable points are sufficient to recover motion parameters from two frames under orthogonal projection and that five points are sufficient to simplify the solution of the two-frame problem under orthogonal projection to solving a linear equation system.