Loading...
| Friend's email | |
| Your name | |
| Your email | |
| enter code | |
This page was sent successfuly
- Type of Document: M.Sc. Thesis
- Language: Farsi
- Document No: 42082 (19)
- University: Sharif University of Technology
- Department: Computer Engineering
- Advisor(s): Kasaei, Shohreh
- Abstract:
- In this thesis we will first review the problem of deformable modeling. Due to their corss-disciplinary nature, deformable modeling techniques have been the subject of the vigorous research over the past three decades and have found numerous applications in the field of machine vision. Thus the focus will be on general deformable models for computer-based modeling which can be used for computer graphics, visualization, and various image processing applications. So the state of the art of deformable modeling is discussed. Then the focus of the thesis will be on different approaches for the problem of deformable surface reconstruction in 3D space. Amongs these methods there are two main classes of techniques that have proved most effective so far: The template-based methods that rely on establishing correspondences with a reference image in which the shape is already known, and non-rigid structure-from-motion techniques that exploit points tracked across the sequences to reconstruct a completely unknown shape. The focus of the thesis, however, is the former approach. The distinction of this thesis is twofold. First we have considered the problem of noisy dataset. A well-known de-nosing method has been exploited to remedy the effect of the severe noise on the image data. This make it possible to have less reconstruction error that the previous methods in case of high amplitude of noise on the data. Second and most important contribution of the work is the method which has been proposed to do the optimization process of the surface reconstruction. Using adaptive weighting of the inextensibility term of the cost function, the less computational time was achieved while the reconstruction error has not a considerable change.
- Keywords:
- Three Dimensional Reconstruction ; Optimization ; Deformable Surface ; Template Image ; Adaptive Weighting ; Soft Thersholding
Digital Object List
-
محتواي پايان نامه
- view
Bookmark