Abstract:

Existing simulation methods for aircraft type identification mainly focus on a single sensor and a single target. They do not consider the joint acquisition of aircraft parameters by various sensor devices such as optoelectronics, radar, and electronic detection in real scenarios, leading to the simple simulation scenarios. This paper proposes a simulation platform based on multi-source sensors. Specifically, the platform includes an infrared image simulator that uses a cycleGAN network to generate infrared images of the aircraft, a flight simulator that adopts the three-degree-of-freedom flight control method to generate the movement trajectory of the aircraft, a radar simulator, that applies ellipsoidal equations to simulate radar cross-section of the target, an electromagnetic simulator, which simulates a complex electromagnetic environment through typical signal source collection and random noise introduction. Experimental results on the simulation dataset show that the introduction of multiple sensor information can effectively improve the recognition results of target types and improve the ability of the model to assist decision-making.

Key words: multi-source sensor, aircraft simulation, infrared image simulator, trajectory simulator, radar simulator, electromagnetic simulator