[author_cn_name].[cn_title][J].空军工程大学学报:自然科学版,[year_id],[volume]([issue]):[start_page]-[end_page] 深度卷积网络多目标无人机信号检测方法-Research on Deep Convolutional Network Multi-Target UAV Signal Detection Method
文章摘要
史浩东,卢虎,卞志昂.深度卷积网络多目标无人机信号检测方法[J].空军工程大学学报:自然科学版,2021,22(4):29-34
深度卷积网络多目标无人机信号检测方法
Research on Deep Convolutional Network Multi-Target UAV Signal Detection Method
  
DOI:
中文关键词: 无人机  信号检测  识别分类  卷积神经网络  链路感知
英文关键词: UAV  signal detection  identification classification  convolution neural network  link perception
基金项目:
作者单位
史浩东,卢虎,卞志昂 空军工程大学信息与导航学院 西安 710077 
摘要点击次数: 101
全文下载次数: 57
中文摘要:
      现有无人机的感知识别方法多采用视觉探测,易受限于探测距离和周围建筑物遮挡及不良天气能见度等诸多因素的影响。针对这一问题提出一种利用深度卷积神经网络开展无人机链路感知识别的算法,构建多模式多类型无人机的RF信号训练数据集,并给出卷积神经网络详细设计及优化方法步骤。实测结果表明:所提深度算法不仅可以实现多类型的无人机入侵识别,还可以进一步对其型号和飞行模式进行区分。在-20 dB的低信噪比条件下,对无人机批次识别率为96.8%(6类),飞行模式的识别率可达94.4%(12类),具有很强的应用前景。
英文摘要:
      Awareness of existing unmanned aerial vehicle identification method being visual detection, and easily affected by weather changes and many other factors such as visible detection range, and the surrounding buildings shade, etc., a convolution of the neural network based on depth unmanned aerial vehicle link perceptual recognition algorithm is proposed, giving a multi mode multi type uavs RF signal database build steps, and the proposed convolution neural network is designed and optimization method is made in detail. The measured results show that the depth algorithm proposed in this paper can not only realize multi batch and multi target UAV intrusion identification, but also further distinguish its model from flight mode. Under condition of low signal to noise ratio as low as -20 dB, the uav batch identification rate is 96.8% (6 categories), and the flight mode identification rate is 94.4% (12 categories). This method is prosperous in a strong application.
查看全文   查看/发表评论  下载PDF阅读器
关闭