Site Network: Personal | My Company | Vision Research Lab @ UCSB |

 

The RANdom SAmple Conesenus algortihm is used to estimate parameters in presence of a large number of outliers. We are investigating in efficient techniques to improve the stability of the estimates and to reduce their bias, even in presence of multiple instances of the same model.

 

with Dr. C. Kenney, Dr. M. Bober and Prof. B. S. Manjunath

(2004-now) In this project we are trying to construct a RANSAC framework that will enable us to perform parameter estimation robustly in different scenarios characterized by the presence of large quantities of outliers. We are developing methods that will speed up the convergence of the traditional algorithm, that will allow us to perform the fusion of information coming from different sources and that can cope with the presence of multiple models. We are also interested in characterizing the stability of the solutions found by RANSAC.

 

Related Publications

  1. M. Zuliani, C. S. Kenney and B. S. Manjunath,
    "The Multiransac Algorithm and its Application to Detect Planar Homographies"
    Proc. IEEE International Conference on Image Processing, Genova, Italy, Sep. 2005.
    VRL ID 148: [abstract] [PDF] [BibTex]

    Abstract preview: "A RANSAC based procedure is described for detecting inliers corresponding to multiple models in a given set of data points. The algorithm we present in this paper (called multiRANSAC) on average perfo..." [more]

Click here for the ICIP 2005 presentation.

 

Notes and Tutorials

RANSAC for Dummies

This is my take on RANSAC: a simple tutorial that explains the algorithm and presents some estimation techniques which can be useful to people working in the image analysis field. The tutorial is based on the RANSAC toolbox for Matlab which can be downloaded from Github (if you have git installed on your system just type from the command line git clone https://github.com/RANSAC/RANSAC-Toolbox). Click here to download the pdf document.