NORMA eResearch @NCI Library

Micro-UAV Detection using Mask R-CNN

Maske, Shubham Rajabhau (2021) Micro-UAV Detection using Mask R-CNN. Masters thesis, Dublin, National College of Ireland.

[thumbnail of Master of Science]
Preview
PDF (Master of Science)
Download (3MB) | Preview
[thumbnail of Configuration manual]
Preview
PDF (Configuration manual)
Download (1MB) | Preview

Abstract

With the advancement in production of micro-UAV, they have become cheap and easy to operate. While the widespread use of micro-UAVs has provided many benefits to all sectors of society, it has also presented a significant danger to personal, public, and military security. Micro-UAVs are difficult for conventional air-defence systems to identify as they are small in size and have low flying altitude. The proposed research aims in identifying micro-UAVs by implementing deep learning technique. The method presented is a deep learning algorithm called Mask R-CNN, which is a notion for object identification and will be utilized in micro-UAV detection. Publicly available dataset named, Det-Fly, is used in this research. The model is evaluated using mean Average Precision (mAP) as well as validation loss, bounding box loss and classification loss are graphically plotted. A very good results are obtained from the implemented model with mAP value of 72.10%.

Item Type: Thesis (Masters)
Uncontrolled Keywords: Mask R-CNN; Convolutional Neural Network; Micro-UAV; Segmentation; Deep Learning
Subjects: Q Science > QA Mathematics > Electronic computers. Computer science
T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science
Q Science > QA Mathematics > Computer software
T Technology > T Technology (General) > Information Technology > Computer software
Divisions: School of Computing > Master of Science in Data Analytics
Depositing User: Clara Chan
Date Deposited: 07 Dec 2021 17:31
Last Modified: 07 Dec 2021 17:31
URI: https://norma.ncirl.ie/id/eprint/5186

Actions (login required)

View Item View Item