Target classification in infrared imagery by cross-spectral synthesis using GAN

Syeda Nyma Ferdous; Moktari Mostofa; Uche Osahor; Nasser M. Nasrabadi

doi:10.1117/12.2558276

Translator Disclaimer

5 May 2020 Target classification in infrared imagery by cross-spectral synthesis using GAN

Syeda Nyma Ferdous, Moktari Mostofa, Uche Osahor, Nasser M. Nasrabadi

Author Affiliations +

Proceedings Volume 11394, Automatic Target Recognition XXX; 113940B (2020) https://doi.org/10.1117/12.2558276
Event: SPIE Defense + Commercial Sensing, 2020, Online Only

Abstract

Images can be captured using devices operating at different light spectrum's. As a result, cross domain image translation becomes a nontrivial task which requires the adaptation of Deep convolutional networks (DCNNs) to resolve the aforementioned imagery challenges. Automatic target recognition(ATR) from infrared imagery in a real time environment is one of such difficult tasks. Generative Adversarial Network (GAN) has already shown promising performance in translating image characteristic from one domain to another. In this paper, we have explored the potential of GAN architecture in cross-domain image translation. Our proposed GAN model maps images from the source domain to the target domain in a conditional GAN framework. We verify the performance of the generated images with the help of a CNN-based target classifier. Classification results of the synthetic images achieve a comparable performance to the ground truth ensuring realistic image generation of the designed network.

Conference Presentation

Citation Download Citation

Syeda Nyma Ferdous, Moktari Mostofa, Uche Osahor, and Nasser M. Nasrabadi "Target classification in infrared imagery by cross-spectral synthesis using GAN", Proc. SPIE 11394, Automatic Target Recognition XXX, 113940B (5 May 2020); https://doi.org/10.1117/12.2558276

ACCESS THE FULL ARTICLE