Show/Hide Menu
Hide/Show Apps
Logout
Türkçe
Türkçe
Search
Search
Login
Login
OpenMETU
OpenMETU
About
About
Open Science Policy
Open Science Policy
Open Access Guideline
Open Access Guideline
Postgraduate Thesis Guideline
Postgraduate Thesis Guideline
Communities & Collections
Communities & Collections
Help
Help
Frequently Asked Questions
Frequently Asked Questions
Guides
Guides
Thesis submission
Thesis submission
MS without thesis term project submission
MS without thesis term project submission
Publication submission with DOI
Publication submission with DOI
Publication submission
Publication submission
Supporting Information
Supporting Information
General Information
General Information
Copyright, Embargo and License
Copyright, Embargo and License
Contact us
Contact us
Training inverse BRDF with incomplete data for 3D reconstruction through photometric stereo /
Download
index.pdf
Date
2014
Author
Kileci, Samet
Metadata
Show full item record
Item Usage Stats
176
views
95
downloads
Cite This
In this thesis, missing data phenomena seen in a photometric stereo model is dealt with machine learning approaches. Photometric stereo model takes input images acquired with different illuminating conditions and predicts surface properties of an object. Specular regions appear on the images due to reflection for certain angle of light and camera and shadow regions appear because of surface structure of the object and light angle. Since specular and shadow regions degrade the performance of the photometric stereo, in this thesis these regions are handled as regions with missing data by using machine learning approaches. Neural network ensembles are implemented to handle the specular and shadow regions. Networks are trained with full range of BRDF data by omitting the values which have irrelevant intensity information. Once they are trained, test data is assigned to their adequate network by considering the location of missing data. This feature selection and ensemble structure of the networks significantly decrease the effect of missing data. Finally, outputs of each networks are used in the 3D reconstruction, surface structure of the object is successfully obtained with proposed photometric stereo model even in the presence of incomplete data.
Subject Keywords
Computer vision.
,
Image processing.
,
Photometry.
URI
http://etd.lib.metu.edu.tr/upload/12618045/index.pdf
https://hdl.handle.net/11511/24086
Collections
Graduate School of Natural and Applied Sciences, Thesis
Suggestions
OpenMETU
Core
Vibration-based damage identification in beam-like composite laminates by using artificial neural networks
Şahin, Melin (SAGE Publications, 2003-01-01)
This paper investigates the effectiveness of the combination of global (changes in natural frequencies) and local (curvature mode shapes) vibration-based analysis data as input for artificial neural networks (ANNs) for location and severity prediction of damage in fibre-reinforced plastic laminates. A finite element analysis tool has been used to obtain the dynamic characteristics of intact and damaged cantilever composite beams for the first three natural modes. Different damage scenarios have been introdu...
Camera trajectory estimation for indoor robot odometry using stereo images and inertial measurements
Horasan, Anıl; Aksel, Mehmet Haluk; Department of Mechanical Engineering (2016)
In this study, the development and implementation of an algorithm for stereo visual-inertial odometry are described. The study spans the complete process from analyzing the sensory data to the development of a robot odometry algorithm. The criteria for indoor visual-inertial odometry include using low-cost sensor systems, having an error less than five percent of the movement regardless of the distance covered, and building a robust algorithm in the presence of geometric and photometric invariances as well ...
Object recognition and segmentation via shape models
Altınoklu, Metin Burak; Ulusoy, İlkay; Tarı, Zehra Sibel; Department of Electrical and Electronics Engineering (2016)
In this thesis, the problem of object detection, recognition and segmentation in computer vision is addressed with shape based methods. An efficient object detection method based on a sparse skeleton has been proposed. The proposed method is an improved chamfer template matching method for recognition of articulated objects. Using a probabilistic graphical model structure, shape variation is represented in a skeletal shape model, where nodes correspond to parts consisting of lines and edges correspond to pa...
Nonlinear dynamic modeling of gear-shaft-disk-bearing systems using finite elements and describing functions
Maliha, R; Dogruer, CU; Özgüven, Hasan Nevzat (ASME International, 2004-05-01)
This study presents a new nonlinear dynamic model for a gear-shaft-disk-bearing system. A nonlinear dynamic model of a spur gear pair is coupled with linear finite element models of shafts carrying them, and with discrete models of bearings and disks. The nonlinear elasticity term resulting from backlash is expressed by a describing function, and a method developed in previous studies to determine multi harmonic responses of nonlinear multi-degree-of-freedom systems is employed for the solution. The excitat...
Electromagnetic modeling of split-ring resonators
Gurel, Levent; Unal, Alper; Ergül, Özgür Salih (2006-09-15)
In this paper, we report our efforts to model split-ring resonators (SRRs) and their large arrays accurately and efficiently in a sophisticated simulation environment based on recent advances in the computational electromagnetics. The resulting linear system obtained from the simultaneous discretization of the geometry and Maxwell's equations is solved iteratively with the multilevel fast multipole algorithm. As an example, we present an array of 125 SRRs showing a negative effective permeability about 92 GHz.
Citation Formats
IEEE
ACM
APA
CHICAGO
MLA
BibTeX
S. Kileci, “Training inverse BRDF with incomplete data for 3D reconstruction through photometric stereo /,” M.S. - Master of Science, Middle East Technical University, 2014.