An Initial Investigation into Using Convolutional Neural Networks for Classification of Drones

An Initial Investigation into Using Convolutional Neural Networks for Classification of Drones
复制标题

DOI：
10.1109/radar42522.2020.9114745
复制
发表时间：
2020-04
期刊：
2020 IEEE International Radar Conference (RADAR)
影响因子：
--
通讯作者：
H. Dale;C. Baker;M. Antoniou;M. Jahangir
H. Dale;C. Baker;M. Antoniou;M. Jahangir
中科院分区：
其他
文献类型：
--
作者：
H. Dale;C. Baker;M. Antoniou;M. Jahangir

文献摘要

被引文献

相似文献

本文研究了卷积神经网络（CNN）在无人机和非无人机分类中的应用。使用 L 波段凝视雷达获得的雷达频谱图对分类器进行训练，并评估其性能并与机器学习基准进行比较。初步结果表明，CNN 的正确分类性能高达 98.89%。
The use of convolutional neural networks (CNNs) in drone and non-drone classification is investigated in this paper. A classifier is trained on radar spectrograms obtained using an L-band staring radar and the performance is assessed and compared with a machine learning benchmark. Initial results have shown the CNN to achieve a correct classification performance of up to 98.89%.