Paper Title
Drone Detection System Using Region-Based Convolutional Neural Network and Single Shot Detector
Abstract
This study presents an immediate and thorough analysis of previously published works on the detection and
classification of drones via the use of machine learning using a variety of different approaches. Due to the fast growth of
profit-oriented and diversion drones as well as the accompanying threat to the safety of airspace, this research domain has
made progress over the last era. This study will mostly center on several types of identification technologies, including radar,
optical, acoustic, and radiofrequency systems. The results of this study points out that the use of machine learning to the
classification of drones has the potential to be productive. This conclusion is supported by the multiple successful discrete
subscriptions that were examined. On the other hand, the large majority of the research that has been conducted is
exploratory in nature, and it is impossible to compare and contrast the results from the many papers. In the present day, there
is a lack of both a generic requirement-driven enumerating and reference datasets, both of which would be helpful in
conducting an analysis of the many potential solutions to the problem of drone detection and classification. This analysis
would be helpful in determining which of the many potential solutions would be most effective. In this post, I will talk about
the detection of drones as well as a number of technologies, such as SSD, YOLO (You Only Look Once), and Faster RCNN
(Region-based Convolutional Neural Networks) (Single Shot Detector).
Keywords - Drone Detection, Drone Classification, Machine Learning, Convolutional Neural Network (CNN), YOLO, SSD