Name
Title | ||
|---|---|---|
Doppler Radar-based Real-Time Drone Surveillance System Using Convolution Neural Network |
Abstract | ||
|---|---|---|
In recent years, the availability of commercial unmanned air vehicles (UAVs) or drones has enormously increased due to their device miniaturization and low cost. However, the abuse of UAVs can lead to serious security threats among civilians that need to be investigated and prevented. To alleviate these threats, this paper presents a residual convolution neural network-based surveillance system for drone detection. The network is designed with the two-dimensional and unit convolution layer to successively deal with the Doppler radar signatures. The network extracts generic features through the regular convolution layer, where the advanced features are extracted by the four blocks of the processing unit. Doppler radar database is available in the Kaggle repository used for performance evaluation of the proposed network. The empirical results demonstrate that the proposed model acquired 95.92% classification accuracy and outperform the other deep learning models. |
Year | DOI | Venue |
|---|---|---|
2021 | 10.1109/ICTC52510.2021.9620998 | 12TH INTERNATIONAL CONFERENCE ON ICT CONVERGENCE (ICTC 2021): BEYOND THE PANDEMIC ERA WITH ICT CONVERGENCE INNOVATION |
Keywords | DocType | ISSN |
Convolution neural network, drone detection, radar remote sensing, radar detection | Conference | 2162-1233 |
Citations | PageRank | References |
0 | 0.34 | 0 |
Authors | ||
4 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Rubina Akter | 1 | 3 | 2.17 |
| Mohtasin Golam | 2 | 0 | 0.34 |
| Jae-Min Lee | 3 | 0 | 0.68 |
| Dong-Seong Kim | 4 | 0 | 0.68 |