Deep Learning for RF-based Drone Detection and Identification using Welch’s Method is a work by Mahmoud Almasri.
Combining Radio Frequency (RF) with deep learning methods offers a promising solution for detecting the presence of drones. Traditional techniques like radar, vision, and acoustics face several challenges, such as difficulty detecting small drones, false alarms from flying birds or balloons, and performance issues caused by wind. Effective drone detection requires two main stages: feature extraction and feature classification.
This paper proposes a novel approach that includes a new feature extraction method and an optimized deep neural network (DNN). First, the author introduces a method based on Welch’s technique to extract meaningful features from drones’ RF signals. Then, the author considers three optimized DNN models to classify the extracted features.
The first DNN model detects the presence of drones with two classes. The second DNN model detects and recognizes the type of drone with four classes: one for each drone and one for RF background activities. The third model involves ten classes to determine the presence of the drone, its type, and its flight mode (e.g., stationary, hovering, flying with or without video recording).
The proposed approach achieves an average accuracy higher than 94%, significantly improving accuracy by up to 30% compared to existing methods.
Deep Learning for RF-based Drone Detection and Identification using
Welch’s Method contains the following major sections:
- Introduction
- Proposed Approach for Feature Extraction
- Deep Neural Network Model
- Results and Discussion
C-UAS Hub does not own this content and provides a link for users at the bottom of the page to access it in its original location. This allows the author(s) to track important article metrics related to their work. All credit goes to its rightful owner.
Post Image- Parrot Bebop (Post Image Credit: Adobe Stock by Baranov)
