Mercedes García Salguero

I am Mercedes García Salguero, PhD Student associated with the Machine Perception and Intelligent Robotics group (MAPIR), department of Systems Engineering and Automation (ISA), at the University of Málaga (Spain).

E-mail: mercedesgarsal [at] uma.es
Main research interests:
Computer vision; global optimization

Address: Dpto. Ingenieria de Sistemas y Automatica, E.T.S.I. Informatica – Telecomunicacion, Universidad de Malaga, Campus Universitario de Teatinos, 29071 Malaga, Spain

github_logo

Short bio

I was born in Burgos, Spain. I received the B.Sc in “Grado en Ingeniería Electrónica, Robótica y Mecatrónica” (Degree in Electronics, Robotics and Mechatronics) from the University of Málaga in 2018 and the M.Sc in “Mecatrónica” (Mechatronics) in 2019. I am currently pursuing my PhD in “Mecatrónica” under the supervision of Prof. Javier Gonzalez-Jimenez

Topics

Here you can find a list of the topics covered during my thesis and the links to the published articles and available code.

Relative Pose Problem between calibrated cameras

See contributions
  • Certifiable relative pose estimation
    We provide an efficient optimality certifier for this problem. Paper. Code
  • Fast and Robust Certifiable Estimation of the Relative Pose Between Two Calibrated Cameras
    We contribute a fast and efficient certifiable solver and integrate a robust paradigm to detect and discard outliers. Paper. Code
  • A Sufficient Condition of Optimality for the Relative Pose Problem between Cameras
    We provide a sufficient optimality condition that assures the given solution is optimal without computing the full certifier. Paper. Code
  • A Tighter Relaxation for the Relative Pose Problem Between Cameras
    We contribute a set of convex relaxations that estimate the solution even for highly noisy data in less than 7 milliseconds Paper. Code

Relative pose problem with known information

See contributions

  • Fast certifiable relative pose estimation with gravity prior
    We provide an efficient optimality certifier for this problem under four different formulations.
    Code Generic certifier  Paper


Triangulation

See contributions
  • N-view triangulation
    We provide an efficient certifiable solver for this problem. Paper Code
  • Planar 2-view triangulation
    We propose three certifiable algorithms for the planar 2-view triangulation problem where the unknown 3D point is known to belong to a given plane Paper Code

Publications

Here you can find a list of my publications:



Similar Posts