Target Detection and Classification of Small Drones by Deep Learning on Radar Micro-Doppler
Target Detection and Classification of Small Drones by Deep Learning on Radar Micro-Doppler
复制标题
雷达微多普勒深度学习小型无人机目标检测与分类
DOI：
--
复制
发表时间：
2019
期刊：
影响因子：
--
通讯作者：
Niclas Wadströmer
中科院分区：
文献类型：
--
作者：
S. Björklund;Niclas Wadströmer
小型无人机，也称为微型无人机（无人驾驶飞行器），已经变得非常广泛。在安全应用中，通常需要对它们进行检测和分类。在本文中，我们采用雷达微多普勒来检测和分类小型无人机。微多普勒是由目标部分的运动产生的多普勒频移。我们使用小型无人机和鸟类的雷达测量，生成TVD（时间速度图），并使用深度学习分类器来区分无人机和鸟类（目标检测）以及无人机类型（目标分类），效果非常好。与我们早期的 boosting 和 SVM（支持向量机）分类器在相同数据上的分类性能相比，我们的深度学习分类器在分类性能方面有所改进。
Small drones, also called mini-UAVs (Unmanned Aerial Vehicles), have become very wide-spread. In security applications it is often desirable to detect and classify them. In this paper we employ radar micro-Doppler for detection and classification of small drones. Micro-Doppler are Doppler shifts generated by the movements of parts of the target. We have used radar measurements of small drones and birds, generated TVDs (Time Velocity Diagrams), and used a deep learning classifier to distinguish between drones and birds (target detection) and types of drones (target classification) with very good results. Our deep learning classifier is an improvement in classification performance compared to our earlier boosting and SVM (Support Vector Machine) classifiers on the same data.
小型无人机的毫米波微多普勒测量
DOI：
--
发表时间：
2017
期刊：
--
影响因子：
--
作者：
Rahman S.
通讯作者：
Rahman S.