• Journal of the Korea Institute of Military Science and Technology
• /
• v.27 no.6
• /
• pp.665-676
• /
• 2024

Infrared imaging is a powerful non-destructive and non-invasive technique to detect infrared radiations and capture valuable insights inaccessible through the visible spectrum. It has been widely used in the military for reconnaissance, hazard detection, night vision, guidance systems, and countermeasures. There is a huge potential for machine learning models to improve trivial infrared imaging tasks in military applications. One major roadblock is the scarcity and control over infrared imaging datasets related to military applications. One possible solution is to use synthetic infrared images to train machine learning networks. However, synthetic IR images present a domain gap and produce weak learning models that do not generalize well. We investigate adversarial networks and Explainable AI(XAI) techniques to refine synthetic infrared imaging data, enhance their realism, and synthesize refiner networks with XAI. We use a U-Net-based refiner network to refine synthetic infrared data and a PatchGAN discriminator to distinguish between the refined and real IR images. Grad-CAM XAI technique is used for network synthesis. We also analyzed the frequency domain patterns and power spectra of real and synthetic infrared images to find key attributes to distinguish real from synthetic. We tested our refined images on the realism benchmarks using frequency domain analysis.