• 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.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.52 no.11
• /
• pp.115-123
• /
• 2015

The infrared light is known to be less dependent on background light compared to the visible light, and thus many applications such as remote sensing and image surveillance use the infrared image. Similar to color images, infrared images can also be degraded by hazy weather condition, and consequently the performance of the infrared image-based applications can decrease. Nevertheless, infrared image dehazing has not received significant interest. In this paper, we analyze the characteristic of infrared images, especially near-infrared (NIR) images, and present an NIR dehazing algorithm using the analyzed characteristics. In particular, a machine learning framework is adopted to obtain an accurate transmission map and several post-processing methods are used for further refinement. Experimental results show that the proposed NIR dehazing algorithm outperforms the conventional color image dehazing method for NIR image dehazing.