The use of small and remotely controlled unmanned aerial vehicles (UAVs), or drones, has increased in recent years. This goes in parallel with misuse episodes, with an evident threat to the safety of people or facilities. As a result, the detection of UAV has also emerged as a research topic. Most studies on drone detection fail to specify the type of acquisition device, the drone type, the detection range, or the dataset. The lack of proper UAV detection studies employing thermal infrared cameras is also an issue, despite its success with other targets. Besides, we have not found any previous study that addresses the detection task as a function of distance to the target. Sensor fusion is indicated as an open research issue as well, although research in this direction is scarce too. To counteract the mentioned issues and allow fundamental studies with a common public benchmark, we contribute with an annotated multi-sensor database for drone detection that includes infrared and visible videos and audio files. The database includes three different drones, of different sizes and other flying objects that can be mistakenly detected as drones, such as birds, airplanes or helicopters. In addition to using several different sensors, the number of classes is higher than in previous studies. To allow studies as a function of the sensor-to-target distance, the dataset is divided into three categories (Close, Medium, Distant) according to the industry-standard Detect, Recognize and Identify (DRI) requirements, built on the Johnson criteria. Given that the drones must be flown within visual range due to regulations, the largest sensor-to-target distance for a drone is 200 m, and acquisitions are made in daylight. The data has been obtained at three airports in Sweden: Halmstad Airport (IATA code: HAD/ICAO code: ESMT), Gothenburg City Airport (GSE/ESGP) and Malm\"o Airport (MMX/ESMS).
翻译:近年来,使用小型和遥控无人驾驶飞行器(无人驾驶飞行器)或无人驾驶飞机(无人驾驶飞行器)的情况有所增加。这与误用事件同时发生,明显威胁到人或设施的安全。结果,无人驾驶飞行器的探测也成为一个研究课题。关于无人驾驶飞行器探测的大多数研究未能具体说明获取装置的类型、无人驾驶飞行器的类型、探测范围或数据集。缺乏使用热红外红外照相机的适当无人驾驶飞行器探测研究也是一个问题。此外,我们没有发现以往任何研究将探测任务作为距离目标的函数的研究。传感器的合并也表明是一个公开的研究问题,尽管这方面的研究也很少。为了应对上述问题,并允许以公共基准进行基础研究,我们利用一个附加说明的多传感器数据库来进行无人驾驶飞行器的探测,其中包括红外和可见的视频和音频档案。数据库包括三个不同的无人驾驶飞机、不同尺寸和其他飞行物体,如鸟、飞机或直升机等,而且可以误测得的无人驾驶无人驾驶飞行器。Sensortar NSO的频率和直径直径直径飞行机的频率,除了使用若干次的直径直径飞行机机机机级的轨道,在市级的飞行机机机机机上,此外的机级的轨道上,还有三级的轨道的轨道的轨道的轨道的轨道上的轨道上的轨道上的飞行,此外的轨道的轨道是前三代码。在前的轨道的轨道上的轨道上的轨道上的轨道上的轨道上的轨道上的轨道上的轨道,在前代算。