Show simple item record

dc.contributor.advisorErdem, Arif Tanju
dc.contributor.authorKiliç, Selçuk
dc.date.accessioned2020-12-06T14:17:23Z
dc.date.available2020-12-06T14:17:23Z
dc.date.submitted2014
dc.date.issued2018-08-06
dc.identifier.urihttps://acikbilim.yok.gov.tr/handle/20.500.12812/103638
dc.description.abstractKonum belirleme ve SLAM problemleri robotik yaynlarnda yuksek ilgi toplams vedegisik ortamlarda, bir insansz ajann basar ile calsabilmesi icin onemi kaydedilmistir.Bu problemler icin bulunan cozumlerin basarl olanlar genellikle Genisletilmis KalmanFiltreleri ve Parcack Filtreleri gibi gurultu ltreleri temellidir. Bu problemler belirtilenltrelerin kullanm ile temel olarak veri eslestirme problemine indirgenir. Bukonu uzerine de son yllardaki robotik yaynlarnda yuksek ilgi toplanms ve cesitlicozumler onerilmistir.Bu tez raporunda ilk olarak en cok calslms veri eslestirmeyontemleri, ornegin Joint Compatibility, Sequential Compatibility Nearest Neighbor,Joint Maximum Likelihood, one point RANSAC ve epipolar uygunluk yontemleri incelenmistir. _Ikinci bolumde ise RANSAC ve epipolar geometri tabanl yeni bir yontemolan One-Point RANSAC with Epipolar Constraint (OPRF) sunulmustur. Bu metodunepipolar uygunluk yontemi ile performans ve tutarllk acsndan karslastrmasonuclar da eklenmistir.
dc.description.abstractThe problem of Localization or Simultaneous Localization and Mapping has receiveda great deal of attention within the robotics literature, and the importance of thesolutions to this problem has been well documented for successful operation of autonomousagents in a number of environments. Of the numerous solutions that havebeen developed for solving the problems, many of the most successful approachescontinue to either rely on, or stem from noise ltering techniques, especially the ExtendedKalman Filter method or Particle Filtering methods. Localization problemsare downgraded to a data association problem after using mentioned lters. This topichas 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, JointMaximum Likelihood, one point RANSAC and epipolar consistency, are studied. Asthe second part of the thesis a new method is presented. One-Point RANSAC withEpipolar Constraint (OPRF) is based on RANSAC and epipolar geometry. Later theperformance and consistency of the method will be compared to epipolar consistencysolution.en_US
dc.languageEnglish
dc.language.isoen
dc.rightsinfo:eu-repo/semantics/openAccess
dc.rightsAttribution 4.0 United Statestr_TR
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/
dc.subjectBilgisayar Mühendisliği Bilimleri-Bilgisayar ve Kontroltr_TR
dc.subjectComputer Engineering and Computer Science and Controlen_US
dc.titleA new method for data association in 3-d localization: One-point ransac with epipolar constraint
dc.title.alternativeÜç boyutlu konumlandırma problemleri için yeni bir veri eşleştirme çözüm yöntemi: One-poınt ransac wıth epıpolar constraınt
dc.typemasterThesis
dc.date.updated2018-08-06
dc.contributor.departmentBilgisayar Bilimleri ve Mühendisliği Anabilim Dalı
dc.identifier.yokid10048799
dc.publisher.instituteFen Bilimleri Enstitüsü
dc.publisher.universityÖZYEĞİN ÜNİVERSİTESİ
dc.identifier.thesisid371124
dc.description.pages42
dc.publisher.disciplineDiğer


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record

info:eu-repo/semantics/openAccess
Except where otherwise noted, this item's license is described as info:eu-repo/semantics/openAccess