Tools
Tools
Saji, Albin (2024) Enhancing Land Use Classification through Deep Learning with UAV Imagery. Masters thesis, Dublin, National College of Ireland.
Preview |
PDF (Master of Science)
Download (1MB) | Preview |
Preview |
PDF (Configuration Manual)
Download (822kB) | Preview |
Abstract
Land all around the world has various uses. In particular, tracking land use is one of the crucial tasks that a government can perform to track urban planning, environmental monitoring and even disaster management. The following task is both time-consuming and prone to errors when done traditionally. This research study proposes the adoption of deep learning models for land classification using the UAV imagery data. The study proposes the use of CNN networks and various architectures to detect the land using a pre-labelled dataset. The study has incorporated the CRISP-DM approach for land classification, and four different architectures are built, including, CNN, Alex-Net, VGg-16, and ResNet-50, where the ResNet-50 attained the maximum accuracy showcasing the advantage of deep learning and deep architectures for a given problem.
| Item Type: | Thesis (Masters) |
|---|---|
| Supervisors: | Name Email Hamill, David UNSPECIFIED |
| Subjects: | H Social Sciences > HD Industries. Land use. Labor Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science Q Science > QH Natural history > QH301 Biology > Methods of research. Technique. Experimental biology > Data processing. Bioinformatics > Artificial intelligence Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Artificial intelligence Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning |
| Divisions: | School of Computing > Master of Science in Data Analytics |
| Depositing User: | Ciara O'Brien |
| Date Deposited: | 25 Aug 2025 10:55 |
| Last Modified: | 25 Aug 2025 10:55 |
| URI: | https://norma.ncirl.ie/id/eprint/8622 |
Actions (login required)
 |
View Item |