Deep learning for anisoplanatic optical turbulence mitigation in long-range imaging

نویسندگان

چکیده

We present a deep learning approach for restoring images degraded by atmospheric optical turbulence. consider the case of terrestrial imaging over long ranges with wide field-of-view. This produces an anisoplanatic scenario where turbulence warping and blurring vary spatially across image. The proposed mitigation (TM) method assumes that sequence short-exposure is acquired. A block matching (BM) registration algorithm applied to observed frames dewarping, resulting are averaged. convolutional neural network (CNN) then employed perform adaptive restoration. refer TM as CNN (BM-CNN) method. Training accomplished using simulated data from fast simulation tool capable producing large amount imagery declared truth rapidly. Testing done independent different well-validated numerical wave-propagation simulator. Our BM-CNN evaluated in number experiments quantitative metrics. analysis made possible virtue having simulations. restored provided subjective evaluation. demonstrate outperforms benchmark methods scenarios tested.

برای دانلود رایگان متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Full-range imaging of eye accommodation by high-speed long-depth range optical frequency domain imaging

We describe a high-speed long-depth range optical frequency domain imaging (OFDI) system employing a long-coherence length tunable source and demonstrate dynamic full-range imaging of the anterior segment of the eye including from the cornea surface to the posterior capsule of the crystalline lens with a depth range of 12 mm without removing complex conjugate image ambiguity. The tunable source...

متن کامل

Long-Range Correlations in Deep-Inelastic Scattering

Multiplicity correlations between the current and target regions of the Breit frame in deep-inelastic scattering processes are studied. It is shown that the correlations are sensitive to the first-order perturbative QCD effects and can be used to extract the behavior of the boson-gluon fusion rates as a function of the Bjorken variable. The behavior of the correlations is derived analytically a...

متن کامل

Long-Range Correlations in Deep-Inelastic Scattering

Multiplicity correlations between the current and target regions of the Breit frame in deep-inelastic scattering processes are studied. It is shown that the correlations are sensitive to the first-order perturbative QCD effects and can be used to extract the behavior of the boson-gluon fusion rates as a function of the Bjorken variable. The behavior of the correlations is derived analytically a...

متن کامل

Inertial range scaling in rotations of long rods in turbulence.

We derive a scaling relationship for the mean square rotation rate of rods with lengths in the inertial range in turbulence: ∝ l(-4/3). We present experimental measurements of the rotational statistics of neutrally buoyant rods with lengths 2.8<l/η<72.9, and find that the measurements approach the predicted scaling. The approach to inertial range scaling is shown to be more complex t...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

ژورنال

عنوان ژورنال: Optical Engineering

سال: 2021

ISSN: ['1560-2303', '0091-3286']

DOI: https://doi.org/10.1117/1.oe.60.3.033103