Robust multiple homography estimation: an ill-solved problem

Files

RA_hdl_107900.pdf (288.54 KB)
  (Restricted Access)

Date

2015

Authors

Szpak, Z.
Chojnacki, W.
Van Den Hengel, A.

Editors

Advisors

Journal Title

Journal ISSN

Volume Title

Type:

Conference paper

Citation

Proceedings / CVPR, IEEE Computer Society Conference on Computer Vision and Pattern Recognition. IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2015, vol.07-12-June-2015, pp.2132-2141

Statement of Responsibility

Zygmunt L. Szpak, Wojciech Chojnacki, Anton van den Hengel

Conference Name

IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (7 Jun 2015 - 12 Jun 2015 : Boston, MA)

Abstract

The estimation of multiple homographies between two piecewise planar views of a rigid scene is often assumed to be a solved problem. We show that contrary to popular opinion various crucial aspects of the task have not been adequately emphasised. We are motivated by a growing body of literature in robust multi-structure estimation that purports to solve the multi-homography estimation prob- lem but in fact does not. We demonstrate that the estima- tion of multiple homographies is an ill-solved problem by deriving new constraints that a set of mutually compatible homographies must satisfy, and by showing that homogra- phies estimated with prevailing methods fail to satisfy the requisite constraints on real-world data. We also explain why incompatible homographies imply inconsistent epipo- lar geometries. The arguments and experiments presented in this paper signal the need for a new generation of robust multi-structure estimation methods that have the capacity to enforce constraints on projective entities such as homog- raphy matrices.

School/Discipline

Dissertation Note

Provenance

Description

Access Status

Rights

© 2015 IEEE

License

Grant ID

Call number

Persistent link to this record