Nowadays, radar-based surveillance systems already consist of highly complex tracking, sensor data fusion, and identification algorithms, which track the trajectories of moving objects. They are embedded in a real-time middleware with a straight forward processing chain according to the Joint Directors of Laboratories (JDL) fusion model. With the spread of new technologies, e.g., big data, distributed data processing and machine learning open up new possibilities for surveillance systems. Commercial data providers provide trajectories of all kinds of vessels and aircraft worldwide. Best known are automatic dependent surveillance-broadcast and (satellite-) automatic identification system used in air and maritime surveillance. Both are cooperative systems and, meanwhile, also integrated as the sensor source in surveillance systems. An advantage of these trajectories is that in addition to the unique identification of the object by an identifier, e.g., International Civil Aviation Organization code or Maritime Mobile Service Identity (MMSI), with which they can be easily assigned to the generating objects contain additional context data that can be used as labels for supervised machine learning. In addition, they are similar in structure to radar tracks and are, therefore, ideal for analysis and training of learning algorithms. This article gives an overview of how these new technologies in combination with big data of trajectories can be integrated into existing surveillance systems and how machine learning can help to improve situational awareness. It is intended as an overview to show which data and which methods open up new opportunities.

中文翻译：

---

基于雷达的监控系统的机器学习支持


如今，基于雷达的监视系统已经包含高度复杂的跟踪、传感器数据融合和识别算法，可跟踪移动物体的轨迹。根据实验室联合主任 (JDL) 融合模型，它们嵌入到具有直接处理链的实时中间件中。随着大数据等新技术的传播，分布式数据处理和机器学习为监控系统开辟了新的可能性。商业数据提供商提供全球各种船舶和飞机的轨迹。最著名的是用于空中和海上监视的自动相关监视广播和（卫星）自动识别系统。两者都是协作系统，同时也集成为监控系统中的传感器源。这些轨迹的优点是，除了通过标识符（例如国际民用航空组织代码或海上移动服务身份（MMSI））对对象进行唯一标识之外，还可以轻松地将它们分配给生成对象，并包含附加上下文可用作监督机器学习的标签的数据。此外，它们的结构与雷达轨迹相似，因此非常适合学习算法的分析和训练。本文概述了如何将这些新技术与轨迹大数据相结合集成到现有的监控系统中，以及机器学习如何帮助提高态势感知能力。它旨在作为一个概述来显示哪些数据和哪些方法开辟了新的机会。