Rockfall Detection on Mars using Deep Learning Algorithm

Dutta Bhowmik, Soumi (2022) Rockfall Detection on Mars using Deep Learning Algorithm. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (1MB) | Preview
Preview	PDF (Configuration manual) Download (364kB) | Preview

Abstract

The aim of this project is to detect the rockfall on Mars which helps to learn about the surface of Mars and its formation and frequency of it. The trails of this rockfall can help to do the surface analysis for the scientist. Previously all these used happen just by doing manual mappings. The manual technique has its own drawbacks like time consumption and providing less information. Recently there are few research happened which showed good success for rockfall detection by data analysing. This research provides Deep learning approach for the same as there are studies in crater detection, rockfall detection on Moon. In this research three models have been chosen and compared like CNN, VGG16 and VGG19. CNN has given accuracy of 67% and VGG16 is at 94% and VGG19 is at 48%.

Item Type:	Thesis (Masters)
Subjects:	Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science Q Science > QB Astronomy Q Science > QE Geology Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning
Divisions:	School of Computing > Master of Science in Data Analytics
Depositing User:	Tamara Malone
Date Deposited:	24 Jan 2023 14:38
Last Modified:	03 Mar 2023 12:56
URI:	https://norma.ncirl.ie/id/eprint/6116

Actions (login required)

View Item