AKPABIO, INYENEOBONG EFFIONG and Covenant University, Theses (2023) DEVELOPING A PREDICTIVE MODEL FOR FACILITATING DRONE LANDING. Masters thesis, COVENANT UNIVERSITY.
![[img]](http://eprints.covenantuniversity.edu.ng/style/images/fileicons/application_pdf.png) |
PDF
Download (189kB) |
Abstract
Drones are one of the leading technological improvements of the 21st century and have a wide range of use in different fields of human endeavor: Military, Retail, and Medicine amongst other fields. The increasing use of drone in day to day like unfortunately comes with dangers as the number of damages and injuries increase with the increase in use of drones especially with respect to safely landing of the drones in cases of emergency. In Particular the use of autonomous drones has also seen increase number of usage in recent times. These unmanned aerial vehicles can perform majority of drone activities such as navigation, acceleration, landing, surveillance e.t.c with little to no human intervention. Landing is one such activity that yields dangers such as injury or loss of property. To mitigate this problem, this study aims to develop a model to analyze images and determine if the image represents a landmark that is safe for emergency landing of the drones. Across Literature several approaches exist to achieve autonomous drone landing, it can be broken down broadly into visual and non-visual approaches. Our study focuses on the visual approach, utilizing landmark images captured by the drone live camera.The image will then be processed by the deep learning model that utilizes convolutional neural network that will predict if the image is a safe landmark for landing. The other visual approach involves using a marker or co-operative target to mark where is safe for the drone to land with the obvious drawback of needing to pre-install the marker. Our solution also mitigates the need to have a marker installed before autonomous drone landing can be accomplished.
| Item Type: | Thesis (Masters) |
|---|---|
| Uncontrolled Keywords: | Drones, Drone Landing, Image Classification, CNN, Deep Learning, Machine Learning, Transfer Learning. |
| Subjects: | Q Science > Q Science (General) Q Science > QA Mathematics > QA75 Electronic computers. Computer science |
| Divisions: | Faculty of Engineering, Science and Mathematics > School of Electronics and Computer Science |
| Depositing User: | AKINWUMI |
| Date Deposited: | 03 Oct 2023 12:15 |
| Last Modified: | 03 Oct 2023 12:15 |
| URI: | http://eprints.covenantuniversity.edu.ng/id/eprint/17329 |
Actions (login required)
 |
View Item |
