AAU Student Projects - visit Aalborg University's student projects portal
A master thesis from Aalborg University

Udtræk af 3D struktur ved hjælp af tekstur flow

[Extraction of 3D Structure using Texture Flow]

Author(s)

Term

10. term

Education

Publication year

2008

Submitted on

2008-06-10

Pages

140 pages

Abstract

This report investigates the application of texture flow for direct estimation of local three-dimensional structure of a rigid textured surface moving relative to a fixed perspective camera. Texture flow is defined here as a spatiotemporal gradient, based on the estimation of local image texture densities and its derivatives. A major part of the work deals primarily with computational experiments. A simulation framework was developed for exact simulation of local surface and image texture density. An experimental setup was also built and experimentation with a digital camera and a movable textured surface was attempted. The conclusion is two-fold: (1) In the computational experiments, it was indeed found possible to directly estimate local surface orientation and depth using the estimated texture flow derivatives. Sometimes also for velocities (ego-motion). (2) The camera experiments need further work. The estimation of texture density in real digital images is difficult and the methods chosen for texel segmentation showed to be highly sensitive to the lighting conditions.

Denne rapport undersøger brugen af tekstur flow med det formål at direkte estimere lokal tre-dimensional struktur af en stiv tekstureret overflade, som bevæger sig relativt til et fast perspektiv kamera. Textur flow er her defineret som en rum-tids gradient, baseret på estimeringen af lokale billede-tekstur tætheder og dets afledte. En stor del af arbejdet har fokusuret primært på syntetiske eksperimenter. Et simulerings-framework blev udviklet med det formål at eksakt simulere lokal overflade- og billede-tekstur tæthed. En eksperimentel opstilling blev også bygget og eksperimenter med et digital kamera og en flade i bevægelse blev foretaget. To konklusioner eksisterer: (1) I de syntetiske eksperimenter blev det fundet aldeles muligt at direkte estimere lokal overflade retning of dybde ved brug af de estimerede afledte af billede-tekstur tæthederne. Nogle gange også for hastigheder (egen-bevægelse). (2) Kamera eksperimenterne kræver yderligere arbejde. Estimeringen af tekstur tætheder i rigtige digital billeder er besværligt og de valgte metoder til af segmentering af tekstur-enheder, viste sig at være yderst følsom overfor de benyttede lysforhold.

Keywords

Documents


Colophon: This page is part of the AAU Student Projects portal, which is run by Aalborg University. Here, you can find and download publicly available bachelor's theses and master's projects from across the university dating from 2008 onwards. Student projects from before 2008 are available in printed form at Aalborg University Library.

If you have any questions about AAU Student Projects or the research registration, dissemination and analysis at Aalborg University, please feel free to contact the VBN team. You can also find more information in the AAU Student Projects FAQs.