In the last decades, radar technology has experienced a change in its focus. Whereas in the beginning only the detection and tracking of targets was necessary, with the advance of technology the need to obtain higher spatial resolution has emerged. Consequently, radars have evolved into more flexible devices with the ability to generate high resolution imagery for mapping purposes or target identification [3]. Radars are the most suitable sensors for a rapid and reliable recognition of targets as they can operate in scenarios where visibility is very poor, such as bad weather conditions, smoky and dusty environments, etc. Their ability to resolve targets at a long range as well as their operation under any weather conditions makes them differ from other sensors like thermal or optical ones [2].

Target recognition using radar sensors can be divided into two techniques: cooperative and non-cooperative [1]. Cooperative techniques, known as identification friend or foe (IFF), require the communication between target and radar, while non-cooperative techniques, so-called non-cooperative target identification (NCTI), do not establish any communication with them but rely on the comparison of the measured targets with a reference database. This database is usually populated with actual target measurements obtained in scheduled measurement campaigns [4]; however, it implies the collection of information from a great number of flying targets in different aspect angles and configurations and even so, the main problem lies in the fact that not all existing aircrafts may be measured.

For this reason, other methods have been deployed to populate the database. These methods include measurements in anechoic chamber and electromagnetic simulations [5]. The latter is of great interest due to its low cost and the simplicity of obtaining a vast number of CAD aircraft models for electromagnetic simulations.In Cilengitide this paper a target recognition methodology based on high resolution radar imagery is presented. Algorithms related to high resolution radar image creation and the problems found are introduced, as well as a target recognition methodology based on image cross correlation. High resolution radar image generation and target recognition processes are complex and time consuming. The goal of a NCTI system is the reliable recognition of targets in real time; therefore, studies on the computational burden of the whole process are of great interest.

These studies will make it easy to identify the computationally critical points of the system in order to previously choose an implementation platform that could perform these operations efficiently. Accordingly, the computational burden of the proposed system is revised distinguishing the complexity of image generation from the complexity of target recognition.