Search In this Thesis
   Search In this Thesis  
العنوان
Enhancement of Registration in Augmented Reality Applications /
المؤلف
Al-Basiouny, Eman Mohamed Reda.
هيئة الاعداد
باحث / ايمان محمد رضا احمد البسيوني
مشرف / اماني محمود سرحان
مناقش / طارق الاحمدي الطبيلي
مناقش / تامر مدحت محمد
الموضوع
Control Engineering.
تاريخ النشر
2016.
عدد الصفحات
p 156 . :
اللغة
الإنجليزية
الدرجة
ماجستير
التخصص
الهندسة الكهربائية والالكترونية
تاريخ الإجازة
14/6/2016
مكان الإجازة
جامعة طنطا - كلية الهندسه - Computer and Control Engineering
الفهرس
Only 14 pages are availabe for public view

from 176

from 176

Abstract

In recent years, the existence of virtual objects as new guests to our real world has become an indisputable fact. Augmented Reality (AR) makes it easy for us to interact with them efficiently and intuitively. AR is an exciting technology whose ultimate objective is to melt reality and virtuality and allow the user to see real and virtual environments interacting together and cannot notice that they are two different environments. Recently, AR technology started to be applied in our daily life applications. They are now used in several applications, such as medicine, manufacturing, entertainment, military training, engineering design, consumer design, robotics and learning. Some applications consider the registration accuracy as a critical demand, such as medicine and surgery applications and some other applications do not influenced by the accuracy of registration, such as entertainment or consumer design applications.
Every AR application has to detect and calculate the position and orientation of the user’s camera relative to the entities in the real world scene continuously. In general, tracking methods can be divided into two types: sensor-based and vision-based. Vision-based tracking methods are classified into: marker-based tracking and marker-less (natural features) tracking. In marker-based tracking, fiducial markers are placed in the scene to find correspondences between their images and their known 3D locations in the world. On the other hand, in marker-less tracking the correspondences are found between images of real entities in the scene and their known 3D locations in the real world.