Dean Graham Jarvis
Exploring the usage of edge gradients within images to perform coarse localisation
Jarvis, Dean Graham
Authors
Contributors
Theocharis Kyriacou
Supervisor
Abstract
With the rise in autonomous systems being integrated into the world around us, it has become increasingly important that theses systems have functions that allow the navigation of environments. One of the key functions is the recognition of the environment in which the system resides. This thesis seeks to contribute to methods that a given system can use to recognise an environment. To do this, an omni-directional camera is used to produce images of locations which contain sharp edges that lay at certain angles. By counting the pixels on these sharp edges and putting them into histograms based on the corresponding angles, a data structure can be formed to describe the location depicted in the image. This data is taken from multiple images over two locations and then compared to one another. These comparisons show that a system can differentiate between images of locations with this data structure showing a significant difference between two locations. Knowing this, it was then analysed how the differentiating ability of this kind of system developed as the amount of locations increased. This was done by increasing the amount of locations and having the system make a decision as to whether two images belong to the same location. This is then compared to how a human participant performed with the exact same image set. This experiment needs to be performed on a larger data set for any kind of statistical significance, however these initial results show that there is a steady decline in the ability to differentiate between images with this system. However the system had a very high false positive rate which is something that should be studied in more detail.
Thesis Type | Thesis |
---|---|
Publicly Available Date | May 30, 2023 |
Award Date | 2021-03 |
Files
JarvisMPhil2021.pdf
(18.3 Mb)
PDF
Downloadable Citations
About Keele Repository
Administrator e-mail: research.openaccess@keele.ac.uk
This application uses the following open-source libraries:
SheetJS Community Edition
Apache License Version 2.0 (http://www.apache.org/licenses/)
PDF.js
Apache License Version 2.0 (http://www.apache.org/licenses/)
Font Awesome
SIL OFL 1.1 (http://scripts.sil.org/OFL)
MIT License (http://opensource.org/licenses/mit-license.html)
CC BY 3.0 ( http://creativecommons.org/licenses/by/3.0/)
Powered by Worktribe © 2024
Advanced Search