Abstract
Air surveillance radar tracking systems present a variety of known problems related to uncertainty and lack of accurately in radar measurements used as source in these systems. In this work, we feature the theoretical aspects of a tracking algorithm based on neural network paradigm where, from discrete measurements provided by surveillance radar, the objective will be to estimate the target state for tracking purposes as accuracy as possible. The absence of an optimal statistical solution makes the featured neural network attractive despite the availability of complex and well-known filtering algorithms. Neural networks exhibit universal mapping capabilities that allow them to be used as a control tool for capturing hidden information about models learned from a dataset. We use these capabilities to let the network learn, not only from the received radar measurement information, but also from the aircraft maneuvering context, contextual information, where tracking application is working, taking into account this new contextual information which could be obtained from predefined, commonly used, and well-known aircraft trajectories. In this case study, the proposed solution is applied to a typical air combat maneuvering, a dogfight, a form of aerial combat between fighter aircraft. Advantages of integrating contextual information in a neural network tracking approach are demonstrated.
Highlights
Tracking algorithms have a widespread use and increased sophistication in aerial control and surveillance systems where current scenarios demand a great capability on the tracking and surveillance of a large number of objects moving across a vast aerial space
To train neural networks used in this case, a set of pursuit curves, with random errors added to the measurements
In this case study the objective is to document a proposal to incorporating contextual information, which can be found in certain aircraft maneuvers, to a typical estimation and tracking process running on any air surveillance radar system
Summary
Tracking algorithms have a widespread use and increased sophistication in aerial control and surveillance systems (both military and civilian) where current scenarios demand a great capability on the tracking and surveillance of a large number of objects moving across a vast aerial space. Some of them are computational complexity and difficulty in accurately modeling fasterturn and coordinated-turn maneuvers and the difficulty in including additional input features for the estimation process This computational complexity is considered critical in typical cases of air control centers where tracking system must estimate hundreds of targets (aircraft) with thousands of measurements in a short period of time, 3–10 seconds, in close coordination with other multiple functions related to this [11]. In the case of a radar tracking system, NN training information can be set up from data extracted directly from the provided radar measurements, and this information can be augmented by contextual information, deriving knowledge from a domain expert from context situation where tracking algorithm is being executed In this work, such contextual information can enclose multiple sensor data and know expected patterns in air maneuvering which probably will define the target behavior. A proposal of neural network tracking algorithm (in a scope of radar air surveillance) dealing with this contextual information, in addition to the classical radar measurement information considered in this kind of algorithms, will be presented
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callMore From: International Journal of Distributed Sensor Networks
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
