Journal of Real-Time Image Processing

, Volume 11, Issue 1, pp 141–154

Speeding-up homography estimation in mobile devices

  • Pablo Márquez-Neila
  • Javier López-Alberca
  • José M. Buenaposada
  • Luis Baumela
Original Research Paper

DOI: 10.1007/s11554-012-0314-1

Cite this article as:
Márquez-Neila, P., López-Alberca, J., Buenaposada, J.M. et al. J Real-Time Image Proc (2016) 11: 141. doi:10.1007/s11554-012-0314-1

Abstract

A critical problem faced by computer vision on mobile devices is reducing the computational cost of algorithms and avoiding visual stalls. In this paper, we introduce a procedure for reducing the number of samples required for fitting a homography to a set of noisy correspondences using a random sampling method. This is achieved by means of a geometric constraint that detects invalid minimal sets. In the experiments conducted, we show that this constraint not only reduces the number of random samples at a negligible computational cost but also balances the processor workload over time preventing visual stalls. In extreme situations of very large outlier proportion and noise level, it reduces in about one order of magnitude the number of required random samples.

Keywords

Mobile devices Random sampling Homography estimation 

Mathematics Subject Classification (2000)

MSC 65D19 

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  • Pablo Márquez-Neila
    • 1
  • Javier López-Alberca
    • 1
  • José M. Buenaposada
    • 2
  • Luis Baumela
    • 1
  1. 1.Departamento de Inteligencia Artificial, Facultad de Informatica Universidad Politecnica de MadridBoadilla del MonteSpain
  2. 2.Departamento de Ciencias de la computacion, Escuela Tecnica Superior de Ingenieria Informatica Universidad Rey Juan CarlosMostolesSpain

Personalised recommendations