Classification of drones and birds using convolutional neural networks applied to radar micro-Doppler spectrogram images
Classification of drones and birds using convolutional neural networks applied to radar micro-Doppler spectrogram images
复制标题
DOI：
10.1049/iet-rsn.2019.0493
复制
发表时间：
2020-05-01
影响因子：
1.7
通讯作者：
Robertson, Duncan A.
中科院分区：
文献类型：
--
作者：
Rahman, Samiur;Robertson, Duncan A.
提出了一种基于卷积神经网络的无人机分类方法。高保真神经网络分类的主要标准是用于训练的大容量和多样性的真实数据集。这项研究的第一个目标是创建一个大型数据库，其中包括飞行中的无人机和鸟类的微多普勒光谱图像。已经创建了两个具有相同图像的独立数据集，一个具有RGB图像，另一个具有灰度图像。RGB数据集用于基于GoogLeNet架构的培训。灰度级数据集用于训练，并在本研究期间开发了一系列架构。每个数据集被进一步分为两类，一类有四类(无人机、鸟类、杂波和噪音)，另一类有两类(无人机和非无人机)。在训练过程中，20%的数据集被用作验证集。训练完成后，用以前看不见的和未标记的数据集对模型进行测试。对所开发的串联网络的验证和测试精度分别为99.6%和94.4%，对于两类分别为99.3%和98.3%。基于GoogLeNet的模型显示，对于所有情况，验证和测试的准确率都在99%左右。
This study presents a convolutional neural network-based drone classification method. The primary criterion for a high-fidelity neural network-based classification is a real dataset of large size and diversity for training. The first goal of the study was to create a large database of micro-Doppler spectrogram images of in-flight drones and birds. Two separate datasets with the same images have been created, one with RGB images and others with greyscale images. The RGB dataset was used for GoogLeNet architecture-based training. The greyscale dataset was used for training with a series of architecture developed during this study. Each dataset was further divided into two categories, one with four classes (drone, bird, clutter and noise) and the other with two classes (drone and non-drone). During training, 20% of the dataset has been used as a validation set. After the completion of training, the models were tested with previously unseen and unlabelled sets of data. The validation and testing accuracy for the developed series network have been found to be 99.6 and 94.4%, respectively, for four classes and 99.3 and 98.3%, respectively, for two classes. The GoogLenet based model showed both validation and testing accuracies to be around 99% for all the cases.