Human crowd detection for drone flight safety using convolutional neural networks
Human crowd detection for drone flight safety using convolutional neural networks
复制标题
使用卷积神经网络进行人群检测以确保无人机飞行安全
DOI：
10.23919/eusipco.2017.8081306
复制
发表时间：
2017
期刊：
影响因子：
--
通讯作者：
A. Tefas
中科院分区：
文献类型：
--
作者：
Maria Tzelepi;A. Tefas
本文提出了一种新的人群检测方法，利用深度卷积神经网络（CNN），用于无人机飞行安全目的。我们工作的目的是提供轻型架构，根据应用程序的计算限制，可以有效区分从无人机捕获的拥挤和非拥挤场景，并提供人群热图，可用于通过定义禁飞区来增强飞行地图的语义。为此，我们首先建议在我们的任务中调整预训练的CNN，完全丢弃全连接层并附加一个额外的卷积层，将其转换为能够生成人群热图的快速全卷积网络。其次，我们提出了一个双损失训练模型，旨在提高人群和非人群类的可分性。实验验证是在为特定任务创建的新无人机数据集上进行的，并表明了所提出的检测器的有效性。
In this paper a novel human crowd detection method, that utilizes deep Convolutional Neural Networks (CNN), for drone flight safety purposes is proposed. The aim of our work is to provide light architectures, as imposed by the computational restrictions of the application, that can effectively distinguish between crowded and non-crowded scenes, captured from drones, and provide crowd heatmaps that can be used to semantically enhance the flight maps by defining no-fly zones. To this end, we first propose to adapt a pre-trained CNN on our task, by totally discarding the fully-connected layers and attaching an additional convolutional one, transforming it to a fast fully-convolutional network that is able to produce crowd heatmaps. Second, we propose a two-loss-training model, which aims to enhance the separability of the crowd and non-crowd classes. The experimental validation is performed on a new drone dataset that has been created for the specific task, and indicates the effectiveness of the proposed detector.