خط مشی دسترسیدرباره ما
ثبت نامثبت نام
راهنماراهنما
فارسی
ورودورود
صفحه اصلیصفحه اصلی
جستجوی مدارک
تمام متن
منابع دیجیتالی
رکورد قبلیرکورد بعدی
Document Type : Latin Dissertation
Language of Document : English
Record Number : 150247
Doc. No : ET22039
Main Entry : Youngrock Yoon
Title Proper : A NEW KALMAN-FILTER BASED FRAMEWORK FOR FAST AND ACCURATE VISUAL TRACKING OF RIGID OBJECTS
Note : This document is digital این مدرک بصورت الکترونیکی می باشد
Abstract : The best of Kalman-.lter based frameworks reported in the literature for rigidobject tracking work well only if the object motions are smooth (which allows fortight uncertainty bounds to be used for where to look for the object features to betracked). In this thesis, we present a new Kalman-.lter based framework that carriesout fast and accurate rigid object tracking even when the object motions are largeand jerky. The new framework has several novel features, the most signi.cant ofwhich is as follows: The traditional backtracking consists of undoing one-at-a-timethe model-to-scene matchings as the pose-acceptance criterion is violated. In ournew framework, once a violation of the pose-acceptance...,..tested for theQ1 PC1 bus cardBoth these projects mere sofixare des elopment efforts tonards contributing to dlfferentaspects of Roboucs and lZ1echatronics projects m the Controls and Roboucs Group..
Subject : Electericl tess
: برق
electronic file name : TL45235.pdf
Title and statement of responsibility and : A NEW KALMAN-FILTER BASED FRAMEWORK FOR FAST AND ACCURATE VISUAL TRACKING OF RIGID OBJECTS [Thesis]
 
 
 
(در صورت عدم وضوح تصویر اینجا را کلیک نمایید)