A new method for data association in 3-D localization: one-point RANSAC with epipolar constraint

Abstract

The problem of Localization or Simultaneous Localization and Mapping has received a great deal of attention within the robotics literature, and the importance of the solutions to this problem has been well documented for successful operation of autonomous agents in a number of environments. Of the numerous solutions that have been developed for solving the problems, many of the most successful approaches continue to either rely on, or stem from noise ltering techniques, especially the Extended Kalman Filter method or Particle Filtering methods. Localization problems are downgraded to a data association problem after using mentioned lters. This topic has also received a great deal of attention in the robotics literature in recent years, and various solutions have been proposed. In the thesis, rst mostly studied methods, such as Joint Compatibility, Sequential Compatibility Nearest Neighbor, Joint Maximum Likelihood, one point RANSAC and epipolar consistency, are studied. As the second part of the thesis a new method is presented. One-Point RANSAC with Epipolar Constraint (OPRF) is based on RANSAC and epipolar geometry. Later the performance and consistency of the method will be compared to epipolar consistency solution.

Konum belirleme ve SLAM problemleri robotik yay nlar nda y uksek ilgi toplam s ve de gi sik ortamlarda, bir insans z ajan n ba sar ile cal sabilmesi i cin onemi kaydedilmi stir. Bu problemler i cin bulunan c oz umlerin ba sar l olanlar genellikle Geni sletilmi s Kalman Filtreleri ve Par cac k Filtreleri gibi g ur ult u ltreleri temellidir. Bu problemler belirtilen ltrelerin kullan m ile temel olarak veri e sle stirme problemine indirgenir. Bu konu uzerine de son y llardaki robotik yay nlar nda y uksek ilgi toplanm s ve ce sitli c oz umler onerilmi stir.Bu tez raporunda ilk olarak en cok cal s lm s veri e sle stirme y ontemleri, orne gin Joint Compatibility, Sequential Compatibility Nearest Neighbor, Joint Maximum Likelihood, one point RANSAC ve epipolar uygunluk y ontemleri incelenmi stir. _Ikinci b ol umde ise RANSAC ve epipolar geometri tabanl yeni bir y ontem olan One-Point RANSAC with Epipolar Constraint (OPRF) sunulmu stur. Bu metodun epipolar uygunluk y ontemi ile performans ve tutarl l k a c s ndan kar s la st rma sonu clar da eklenmi stir.