论文标题
通过融合不同感应方式实时检测和跟踪
Drone Detection and Tracking in Real-Time by Fusion of Different Sensing Modalities
论文作者
论文摘要
自动检测飞行无人机是一个关键问题，它的存在，尤其是未经授权的情况下可以造成风险的情况或损害安全性。在这里，我们设计和评估了多传感器无人机检测系统。结合标准摄像机和麦克风传感器，我们探索了热红外摄像机的使用，指出是一种可行且有希望的解决方案，在相关文献中几乎没有解决。我们的解决方案还集成了鱼眼相机，以监视天空的更大部分，并将其他摄像机转向感兴趣的对象。传感溶液与ADS-B接收器，GPS接收器和雷达模块相辅相成。但是，由于其检测范围有限，我们的最终部署尚未包括后者。即使此处使用的相机的分辨率较低，热摄像头也被证明是与摄像机一样好的可行解决方案。我们作品的另外两个新颖性是创建一个新的公共数据集的多传感器注释数据，该数据集扩大了与现有类别相比的类数量，以及对检测器性能的研究是传感器到目标距离的函数。还探索了传感器融合，表明可以以这种方式使系统更强大，从而减轻对单个传感器的错误检测。
Automatic detection of flying drones is a key issue where its presence, especially if unauthorized, can create risky situations or compromise security. Here, we design and evaluate a multi-sensor drone detection system. In conjunction with standard video cameras and microphone sensors, we explore the use of thermal infrared cameras, pointed out as a feasible and promising solution that is scarcely addressed in the related literature. Our solution integrates a fish-eye camera as well to monitor a wider part of the sky and steer the other cameras towards objects of interest. The sensing solutions are complemented with an ADS-B receiver, a GPS receiver, and a radar module. However, our final deployment has not included the latter due to its limited detection range. The thermal camera is shown to be a feasible solution as good as the video camera, even if the camera employed here has a lower resolution. Two other novelties of our work are the creation of a new public dataset of multi-sensor annotated data that expands the number of classes compared to existing ones, as well as the study of the detector performance as a function of the sensor-to-target distance. Sensor fusion is also explored, showing that the system can be made more robust in this way, mitigating false detections of the individual sensors.
