Turbulence Mitigation, Error Reduction, and Increased Contrast (TURMERIC)

The Submarine Force is phasing out conventional optical periscopes in favor of digital sensor masts that electronically transmit video to the Control Center. However, digital imagery suffers from distortions due to atmospheric turbulence caused by humidity and temperature gradients near the ocean surface. Existing systems for turbulence correction focus mainly on static scenes and rely on precise image alignment of multiple frames to produce clean images, but submarine imagery comes from a moving camera capturing a moving target within a moving scene. This makes alignment infeasible. Also, results must be available quickly; a turbulence correction system suitable for submarines cannot wait for multiple frames before producing output. Therefore, existing systems for correcting blur and loss of contrast cannot be effectively applied to turbulence correction for submarine imagery. To address these shortcomings, we developed Turbulence Mitigation, Error Reduction, and Increased Contrast (TURMERIC), a software system that uses deep learning to correct for atmospheric turbulence in imagery in real time so that watchstanders and automated detection algorithms can optimally detect surface contacts. TURMERIC uses a generative adversarial network (GAN) to intelligently de-blur and enhance the contrast of photonics mast imagery using only a single frame.