A master thesis from Aalborg University
Inverse light estimation: Estimating the light of outdoor scenes through textures
[Omvendt lysestimering: Estimering af lyset af udendørs scener igennem teksturer]
Author(s)
Term
4. term
Education
Publication year
2024
Submitted on
2024-05-28
Pages
39 pages
Abstract
In this project, the focus was on estimating the light settings of an outdoor scene, using textures obtained through the Unity game engine. The implemented system is meant to work with augmented reality, by obtaining information about the scene and estimating the light of that scene. The estimated light can then be used to shade an object that has been inserted into the scene, to make the object blend into the scene. To estimate the light settings, a lighting model was found and implemented using Python. The Python program uses the textures obtained through Unity, to estimate the light settings. The Python program was connected to the Unity project using sockets, and the estimated values were sent through the connection. The system performed mediocre but still showed promise. The estimated values were not accurate when compared with the actual lighting values, but did follow as expected when the lighting changed. The estimated value did make the inserted object blend in, in certain lighting settings. To make a more stable system, more work should be put into the system.
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.